From 19fe1de79ae7a89506b1a025049619efd03c5e29 Mon Sep 17 00:00:00 2001 From: Kujtim Hoxha Date: Tue, 28 Oct 2025 16:03:02 +0100 Subject: [PATCH] chore: fix tests --- internal/agent/agent_test.go | 39 -- internal/agent/common_test.go | 1 + .../anthropic-sonnet/bash_tool.yaml | 73 +-- .../anthropic-sonnet/download_tool.yaml | 130 ++-- .../anthropic-sonnet/fetch_tool.yaml | 296 --------- .../anthropic-sonnet/glob_tool.yaml | 78 +-- .../anthropic-sonnet/grep_tool.yaml | 78 +-- .../anthropic-sonnet/ls_tool.yaml | 78 +-- .../anthropic-sonnet/multiedit_tool.yaml | 182 +++--- .../anthropic-sonnet/parallel_tool_calls.yaml | 77 ++- .../anthropic-sonnet/read_a_file.yaml | 94 +-- .../anthropic-sonnet/simple_test.yaml | 60 +- .../anthropic-sonnet/sourcegraph_tool.yaml | 83 +-- .../anthropic-sonnet/update_a_file.yaml | 185 +++--- .../anthropic-sonnet/write_tool.yaml | 96 +-- .../openai-gpt-5/bash_tool.yaml | 185 +++--- .../openai-gpt-5/download_tool.yaml | 142 +++-- .../openai-gpt-5/fetch_tool.yaml | 255 -------- .../openai-gpt-5/glob_tool.yaml | 100 +-- .../openai-gpt-5/grep_tool.yaml | 134 ++-- .../TestCoderAgent/openai-gpt-5/ls_tool.yaml | 76 ++- .../openai-gpt-5/multiedit_tool.yaml | 546 +++++++++-------- .../openai-gpt-5/parallel_tool_calls.yaml | 164 ++--- .../openai-gpt-5/read_a_file.yaml | 190 +++--- .../openai-gpt-5/simple_test.yaml | 26 +- .../openai-gpt-5/sourcegraph_tool.yaml | 527 +++++----------- .../openai-gpt-5/update_a_file.yaml | 446 +++++++------- .../openai-gpt-5/write_tool.yaml | 136 ++-- .../openrouter-kimi-k2/bash_tool.yaml | 207 +++++-- .../openrouter-kimi-k2/download_tool.yaml | 148 +++-- .../openrouter-kimi-k2/fetch_tool.yaml | 255 -------- .../openrouter-kimi-k2/glob_tool.yaml | 118 ++-- .../openrouter-kimi-k2/grep_tool.yaml | 120 ++-- .../openrouter-kimi-k2/ls_tool.yaml | 94 ++- .../openrouter-kimi-k2/multiedit_tool.yaml | 579 ++++++++++++++++-- .../parallel_tool_calls.yaml | 148 +++-- .../openrouter-kimi-k2/read_a_file.yaml | 134 ++-- .../openrouter-kimi-k2/simple_test.yaml | 24 +- .../openrouter-kimi-k2/sourcegraph_tool.yaml | 305 ++++++--- .../openrouter-kimi-k2/update_a_file.yaml | 300 ++++++--- .../openrouter-kimi-k2/write_tool.yaml | 138 +++-- .../TestCoderAgent/zai-glm4.6/bash_tool.yaml | 66 +- .../zai-glm4.6/download_tool.yaml | 66 +- .../TestCoderAgent/zai-glm4.6/fetch_tool.yaml | 233 ------- .../TestCoderAgent/zai-glm4.6/glob_tool.yaml | 222 ++++--- .../TestCoderAgent/zai-glm4.6/grep_tool.yaml | 108 ++-- .../TestCoderAgent/zai-glm4.6/ls_tool.yaml | 52 +- .../zai-glm4.6/multiedit_tool.yaml | 284 +++++---- .../zai-glm4.6/parallel_tool_calls.yaml | 304 +++------ .../zai-glm4.6/read_a_file.yaml | 224 +++++-- .../zai-glm4.6/simple_test.yaml | 40 +- .../zai-glm4.6/sourcegraph_tool.yaml | 110 ++-- .../zai-glm4.6/update_a_file.yaml | 294 +++++---- .../TestCoderAgent/zai-glm4.6/write_tool.yaml | 58 +- 54 files changed, 4451 insertions(+), 4657 deletions(-) delete mode 100644 internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yaml delete mode 100644 internal/agent/testdata/TestCoderAgent/openai-gpt-5/fetch_tool.yaml delete mode 100644 internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/fetch_tool.yaml delete mode 100644 internal/agent/testdata/TestCoderAgent/zai-glm4.6/fetch_tool.yaml diff --git a/internal/agent/agent_test.go b/internal/agent/agent_test.go index 3719a1150901e621b7998a9f1e7be0a2aa3ef4b8..3bfcf772a568f79aaf327097ef4ccfb520d3b0df 100644 --- a/internal/agent/agent_test.go +++ b/internal/agent/agent_test.go @@ -245,45 +245,6 @@ func TestCoderAgent(t *testing.T) { _, err = os.Stat(examplePath) require.NoError(t, err, "Expected example.txt file to exist") }) - t.Run("fetch tool", func(t *testing.T) { - agent, env := setupAgent(t, pair) - - session, err := env.sessions.Create(t.Context(), "New Session") - require.NoError(t, err) - - res, err := agent.Run(t.Context(), SessionAgentCall{ - Prompt: "fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'", - SessionID: session.ID, - MaxOutputTokens: 10000, - }) - require.NoError(t, err) - assert.NotNil(t, res) - - msgs, err := env.messages.List(t.Context(), session.ID) - require.NoError(t, err) - - foundFetch := false - var fetchTCID string - - for _, msg := range msgs { - if msg.Role == message.Assistant { - for _, tc := range msg.ToolCalls() { - if tc.Name == tools.FetchToolName { - fetchTCID = tc.ID - } - } - } - if msg.Role == message.Tool { - for _, tr := range msg.ToolResults() { - if tr.ToolCallID == fetchTCID { - foundFetch = true - } - } - } - } - - require.True(t, foundFetch, "Expected to find a fetch operation") - }) t.Run("glob tool", func(t *testing.T) { agent, env := setupAgent(t, pair) diff --git a/internal/agent/common_test.go b/internal/agent/common_test.go index 21bdaf1ab501d34a4ac69cc592af7787733e0950..dfb7a5f3257870762daba505aff673b6f51e8b85 100644 --- a/internal/agent/common_test.go +++ b/internal/agent/common_test.go @@ -175,6 +175,7 @@ func coderAgent(r *recorder.Recorder, env env, large, small fantasy.LanguageMode return nil, err } allTools := []fantasy.AgentTool{ + tools.NewWebFetchTool(env.workingDir, r.GetDefaultClient()), tools.NewBashTool(env.permissions, env.workingDir, cfg.Options.Attribution), tools.NewDownloadTool(env.permissions, env.workingDir, r.GetDefaultClient()), tools.NewEditTool(env.lspClients, env.permissions, env.history, env.workingDir), diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yaml index f2df671d06961962a2dc0d05ea8c410918cfb2e4..afc011346829ca5c2c899742508d0193a0246879 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/bash_tool.yaml @@ -25,46 +25,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01Vrcb5K4uiarmFd1jBNtjav","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01GMKh3aFc9rXpTdormEcsJZ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Bash File"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Bash File"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Creation"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Creation"}} event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Basics"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Comman"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":147,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 539.894084ms + duration: 552.794375ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45787 + content_length: 45720 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -81,61 +84,61 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01UhQLFTP5ug2tQ5KLqeVfz2","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3690,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FwGKwkkgasrRJvxzsZNdxp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3690,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01P78K1Ysxvr6rQnfHXGdPRK","name":"bash","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01KhTAFFBJTKyXVaaDxyAken","name":"bash","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"comm"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"com"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"and\": \"ec"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mand"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ho 'h"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"echo 'h"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ell"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ello ba"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh' "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"bash'"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"> test"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" > test"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".tx"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".txt\"}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8770,"output_tokens":60} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8757,"output_tokens":60} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.699040542s + duration: 2.625279959s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46130 + content_length: 46063 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01P78K1Ysxvr6rQnfHXGdPRK\",\"input\":{\"command\":\"echo 'hello bash' \\u003e test.txt\"},\"name\":\"bash\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01P78K1Ysxvr6rQnfHXGdPRK\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"no output\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use bash to create a file named test.txt with content 'hello bash'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01KhTAFFBJTKyXVaaDxyAken\",\"input\":{\"command\":\"echo 'hello bash' \\u003e test.txt\"},\"name\":\"bash\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01KhTAFFBJTKyXVaaDxyAken\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"no output\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -152,26 +155,26 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_017qbtqQJ8Jpd5WqMRHwYuqz","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":72,"cache_read_input_tokens":12460,"cache_creation":{"ephemeral_5m_input_tokens":72,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_016ghiT5gJ5NFHjDhkHdZAqG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":72,"cache_read_input_tokens":12447,"cache_creation":{"ephemeral_5m_input_tokens":72,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":72,"cache_read_input_tokens":12460,"output_tokens":4} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":72,"cache_read_input_tokens":12447,"output_tokens":4} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.2786715s + duration: 2.882943542s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yaml index 0be13052b1f309595d68b0fdb7d6fd76a678796d..229fdc5fa896176faa6e4179d08e3791c6fdf967 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/download_tool.yaml @@ -25,37 +25,34 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_014PmwWLUvYr6qpsePLJgQuG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":160,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_0176QErnAZwcxymibhMK4feV","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":160,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Downloa"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Downloa"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Text"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d File"}} event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" File"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" from"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" from"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Online Example"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Example"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" URL"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" URL"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":160,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9}} + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":160,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } event: message_stop data: {"type":"message_stop" } @@ -65,15 +62,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 659.197333ms + duration: 650.846708ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45840 + content_length: 45773 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -90,110 +87,95 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01D9kcWATzUQJrQUtwrcVxPY","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3703,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3703,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01PqWFCfgnjv4C8PxK7D54aD","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3703,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3703,"ephemeral_1h_input_tokens":0},"output_tokens":6,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01Vsr6u7qZtK9ot2ctZ12Zrv","name":"download","input":{}} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"url\": \"htt"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll download the file an"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ps://exa"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d save it as example.txt."} } - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mple"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"-files"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".onlin"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e-con"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"vert.com/"} } + event: ping + data: {"type": "ping"} - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"document/tx"} } + event: content_block_stop + data: {"type":"content_block_stop","index":0 } - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/example.tx"} } + event: ping + data: {"type": "ping"} - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t\""} } + event: content_block_start + data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01DHhkBPwN8brz4WnbpoGxwB","name":"download","input":{}} } - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", "}} + event: ping + data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"file_pat"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"/tm"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"url\": "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"p/crush"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"\"h"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"-test/Te"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ttps://exa"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stCod"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"mple-file"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"erAgent"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"s.o"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/anth"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"nl"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rop"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ine-con"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ic-"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"vert.c"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sonnet/do"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"om/docume"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"wn"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"nt/txt/examp"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"load_to"}} + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"le.txt\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ol/e"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":", \"file_p"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"xamp"}} + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ath\": \"e"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"le"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"xa"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".txt\"}"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"mple.txt\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":1 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3703,"cache_read_input_tokens":8770,"output_tokens":112} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3703,"cache_read_input_tokens":8757,"output_tokens":104} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop"} headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.465269833s + duration: 3.3062615s - id: 2 request: proto: HTTP/1.1 @@ -239,15 +221,15 @@ interactions: - text/plain; charset=UTF-8 status: 200 OK code: 200 - duration: 256.279125ms + duration: 188.843959ms - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46447 + content_length: 46394 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01Vsr6u7qZtK9ot2ctZ12Zrv\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/example.txt\",\"url\":\"https://example-files.online-convert.com/document/txt/example.txt\"},\"name\":\"download\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Vsr6u7qZtK9ot2ctZ12Zrv\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll download the file and save it as example.txt.\",\"type\":\"text\"},{\"id\":\"toolu_01DHhkBPwN8brz4WnbpoGxwB\",\"input\":{\"file_path\":\"example.txt\",\"url\":\"https://example-files.online-convert.com/document/txt/example.txt\"},\"name\":\"download\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01DHhkBPwN8brz4WnbpoGxwB\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -264,26 +246,26 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01481ctikWtwodyqW5ZfH6UM","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":170,"cache_read_input_tokens":12473,"cache_creation":{"ephemeral_5m_input_tokens":170,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LufXCPJrm7g25PnNRZE3cN","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":161,"cache_read_input_tokens":12460,"cache_creation":{"ephemeral_5m_input_tokens":161,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":170,"cache_read_input_tokens":12473,"output_tokens":4} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":161,"cache_read_input_tokens":12460,"output_tokens":4} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.790234583s + duration: 3.079369708s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yaml deleted file mode 100644 index 81467407d56e71cd61b98c43f000d263b7bd6934..0000000000000000000000000000000000000000 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/fetch_tool.yaml +++ /dev/null @@ -1,296 +0,0 @@ ---- -version: 2 -interactions: -- id: 0 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 844 - host: "" - body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nfetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word ''John Doe''\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}' - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - Anthropic/Go 1.14.0 - url: https://api.anthropic.com/v1/messages - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01CZZNnv73tmgmvZ2hmoE5cq","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":167,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } - - event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Web"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Page"}} - - event: ping - data: {"type": "ping"} - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Content"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Search"}} - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" John"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Doe"} } - - event: content_block_stop - data: {"type":"content_block_stop","index":0 } - - event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":167,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} } - - event: message_stop - data: {"type":"message_stop" } - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 683.59975ms -- id: 1 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 45858 - host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - Anthropic/Go 1.14.0 - url: https://api.anthropic.com/v1/messages - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01MqZfAF7XxVPZNT8xAK3tY1","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3710,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3710,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } - - event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01GvH1YG76cwYSJFq7GwvCsn","name":"fetch","input":{}} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"ur"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"l\": \"htt"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ps://exampl"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e-"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fil"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"es.on"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"line-"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"convert.com"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/website"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/html/exam"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"pl"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e.html\""} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"format\""} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"text\"}"} } - - event: content_block_stop - data: {"type":"content_block_stop","index":0 } - - event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3710,"cache_read_input_tokens":8770,"output_tokens":86} } - - event: message_stop - data: {"type":"message_stop" } - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 3.128834709s -- id: 2 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 0 - host: example-files.online-convert.com - headers: - User-Agent: - - crush/1.0 - url: https://example-files.online-convert.com/website/html/example.html - method: GET - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - uncompressed: true - body: |- - - - - - -

HTML test file

- -

Purpose: Provide example of this file type
- Document file type: HTML
- Version: 1.0
- Remark:

- -

- - Example content:
- The names "John Doe" for males, "Jane Doe" or "Jane Roe" for females, or "Jonnie Doe" and "Janie Doe" for children, or just "Doe" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.

- -

John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series.

- -

Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases.

- -

- - File created by https://www.online-convert.com
- More example files: https://www.online-convert.com/file-type
- Text of "Example content": Wikipedia
- License: Attribution-ShareAlike 3.0 Unported - -

- -

Feel free to use and share the file according to license above.

- - - - headers: - Content-Type: - - text/html; charset=UTF-8 - status: 200 OK - code: 200 - duration: 50.937875ms -- id: 3 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 48743 - host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01GvH1YG76cwYSJFq7GwvCsn\",\"input\":{\"format\":\"text\",\"url\":\"https://example-files.online-convert.com/website/html/example.html\"},\"name\":\"fetch\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01GvH1YG76cwYSJFq7GwvCsn\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"HTML test file Purpose: Provide example of this file type Document file type: HTML Version: 1.0 Remark: Example content: The names \\\"John Doe\\\" for males, \\\"Jane Doe\\\" or \\\"Jane Roe\\\" for females, or \\\"Jonnie Doe\\\" and \\\"Janie Doe\\\" for children, or just \\\"Doe\\\" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of \\\"John Doe\\\" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand. John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series. Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, \\\"John Doe v. Jane Roe\\\". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) \\\"John Doe\\\"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases. File created by https://www.online-convert.com More example files: https://www.online-convert.com/file-type Text of \\\"Example content\\\": Wikipedia License: Attribution-ShareAlike 3.0 Unported Feel free to use and share the file according to license above.\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - Anthropic/Go 1.14.0 - url: https://api.anthropic.com/v1/messages - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Mk5znSN4m9LwM3cu5NYg8x","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":710,"cache_read_input_tokens":12480,"cache_creation":{"ephemeral_5m_input_tokens":710,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } - - event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Yes"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", it contains \"John Doe\" multiple"}} - - event: ping - data: {"type": "ping"} - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" times throughout the document."} } - - event: ping - data: {"type": "ping"} - - event: content_block_stop - data: {"type":"content_block_stop","index":0 } - - event: ping - data: {"type": "ping"} - - event: ping - data: {"type": "ping"} - - event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":710,"cache_read_input_tokens":12480,"output_tokens":18} } - - event: message_stop - data: {"type":"message_stop" } - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 2.120130958s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yaml index c83526494f4b979604499cc26bf38b1062b28a9f..78b0b4831e385240dc7e08fada19b1826f443d94 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/glob_tool.yaml @@ -25,52 +25,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01EumvKhSStGmGrbLhmaD2w9","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01CPU5CFBx4gU6BfdaNchU9Y","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Fin"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Finding"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"}} event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files in Current"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Using"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Glob"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Directory"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":142,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 561.838166ms + duration: 550.872667ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45776 + content_length: 45709 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -87,49 +84,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01RBCKb4e9fgBGbVcSyCEZTH","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3685,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3685,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_015k1kGTjzynrDQafHZAoWhc","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3685,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3685,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_013xZZEt8NRoP1BkMCrdT4Je","name":"glob","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01PW4ZhRrfq6nED1oPe4z8D9","name":"glob","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"p"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pat"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"attern"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tern\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"*.go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"*.go"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3685,"cache_read_input_tokens":8770,"output_tokens":52}} + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3685,"cache_read_input_tokens":8757,"output_tokens":52} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.924670916s + duration: 3.11614625s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46146 + content_length: 46079 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_013xZZEt8NRoP1BkMCrdT4Je\",\"input\":{\"pattern\":\"*.go\"},\"name\":\"glob\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_013xZZEt8NRoP1BkMCrdT4Je\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01PW4ZhRrfq6nED1oPe4z8D9\",\"input\":{\"pattern\":\"*.go\"},\"name\":\"glob\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01PW4ZhRrfq6nED1oPe4z8D9\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -146,29 +143,38 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01VxVCneCMPyx9BuiznBBKCw","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":12455,"cache_creation":{"ephemeral_5m_input_tokens":86,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01K1uo1jgbuP3BTxwm16Cmaa","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":12442,"cache_creation":{"ephemeral_5m_input_tokens":86,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"main"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go"} } + + event: ping + data: {"type": "ping"} event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } + + event: ping + data: {"type": "ping"} + + event: ping + data: {"type": "ping"} event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":12455,"output_tokens":6} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":86,"cache_read_input_tokens":12442,"output_tokens":6} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.43540725s + duration: 6.996937958s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yaml index 4d9267978cdb4fe6a74d0676dd2e0fe13781f90f..b3b6087f4af8d37bb1eee3cc6c0260b329ad5576 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/grep_tool.yaml @@ -25,49 +25,52 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01JTVg8ZKQLYPPbkLsWRjsFg","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01TAzqXe9NYNahvhRrX3aTxA","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching "}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Packages"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"'"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in Go Files with"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"package' in Go Files"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" with"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Grep"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Grep"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":13} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":144,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":15} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 583.795541ms + duration: 585.740833ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45774 + content_length: 45707 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -84,61 +87,58 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01LVDu5sSKkwYjEtpxCD2CKE","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3687,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3687,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_011sstAwLRdvnWk6BWCvVD2C","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3687,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3687,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01Q9etHpriwWJwdiS1savECs","name":"grep","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01BrQ2xfRkjzhMDSq8KeQtDX","name":"grep","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pattern\": "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pattern\":"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"p"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"p"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ackag"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ackage\""}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"incl"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ude\": \"*"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"includ"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e\": \"*.go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go"} } event: content_block_delta data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3687,"cache_read_input_tokens":8770,"output_tokens":69} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3687,"cache_read_input_tokens":8757,"output_tokens":69} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.444773916s + duration: 2.3080145s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46216 + content_length: 46149 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01Q9etHpriwWJwdiS1savECs\",\"input\":{\"include\":\"*.go\",\"pattern\":\"package\"},\"name\":\"grep\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Q9etHpriwWJwdiS1savECs\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use grep to search for the word 'package' in go files\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01BrQ2xfRkjzhMDSq8KeQtDX\",\"input\":{\"include\":\"*.go\",\"pattern\":\"package\"},\"name\":\"grep\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01BrQ2xfRkjzhMDSq8KeQtDX\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -155,28 +155,28 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01AmsgdHDpD2UR3NvhMqDu2N","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":12457,"cache_creation":{"ephemeral_5m_input_tokens":125,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01HTohUehKgMhd4deu5dB7HC","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":12444,"cache_creation":{"ephemeral_5m_input_tokens":125,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 match in main.go at"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 match in main.go:"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" line 1."} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"1"} } event: ping data: {"type": "ping"} event: content_block_stop - data: {"type":"content_block_stop","index":0} + data: {"type":"content_block_stop","index":0 } event: ping data: {"type": "ping"} @@ -185,14 +185,14 @@ interactions: data: {"type": "ping"} event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":12457,"output_tokens":17} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":125,"cache_read_input_tokens":12444,"output_tokens":14} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.684206291s + duration: 2.939075s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yaml index d224fd864cc6d2fe780fdd0f7f97630eff15d04f..174aa62f59188ed2f60ea60089003db2a84d2af1 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/ls_tool.yaml @@ -25,37 +25,28 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01NT5ieoGueTkZSoLTaz16VC","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01MxSBvuGVv8LwW2pUXKyHga","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}} event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Listing Files"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"List"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in Current"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Files"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Directory"} } - - event: ping - data: {"type": "ping"} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in Current Directory"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } - - event: ping - data: {"type": "ping"} - - event: ping - data: {"type": "ping"} + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":140,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} } event: message_stop data: {"type":"message_stop" } @@ -65,15 +56,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 550.03325ms + duration: 603.125375ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45768 + content_length: 45701 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -90,37 +81,43 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_014bCjW6RXjGAfM1VD6zQc2a","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3683,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3683,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_014oamANtGHWhzgrh6E6maRy","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3683,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3683,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_018mrbLHzAo3dWWfbXFHZopN","name":"ls","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01GukFkW1CrLVnWMXbQRxedQ","name":"ls","input":{}}} + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"path\":"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \".\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0} + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3683,"cache_read_input_tokens":8770,"output_tokens":34} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3683,"cache_read_input_tokens":8757,"output_tokens":50} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 4.463182791s + duration: 3.758742125s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46142 + content_length: 46085 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_018mrbLHzAo3dWWfbXFHZopN\",\"input\":{},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_018mrbLHzAo3dWWfbXFHZopN\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use ls to list the files in the current directory\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01GukFkW1CrLVnWMXbQRxedQ\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01GukFkW1CrLVnWMXbQRxedQ\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -137,29 +134,38 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_015yiCMxaJv5addgqVM6cyQG","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":81,"cache_read_input_tokens":12453,"cache_creation":{"ephemeral_5m_input_tokens":81,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01W7AdvpkrUzuBJvhqP1vFMp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":97,"cache_read_input_tokens":12440,"cache_creation":{"ephemeral_5m_input_tokens":97,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"go"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".mod, main.go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".mod, main.go"} } + + event: ping + data: {"type": "ping"} event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0} + + event: ping + data: {"type": "ping"} + + event: ping + data: {"type": "ping"} event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":81,"cache_read_input_tokens":12453,"output_tokens":10} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":97,"cache_read_input_tokens":12440,"output_tokens":10} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.459264458s + duration: 2.854635708s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yaml index 3b6cd50e862f83e42995a319804a77ec26e8ee91..82434040e341ff39e00e13be2b381be519e57260 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/multiedit_tool.yaml @@ -25,49 +25,52 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01PE7VYhsyq2iDhiirgYXrnD","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01L6UHdS4q4fVV4eePz13WjK","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Modify"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Edit"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Program"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Code"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Modification"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Greeting"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Request"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":170,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.83986725s + duration: 520.542167ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45854 + content_length: 45787 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -84,91 +87,91 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Kmow4QF1jH1HYBdFiPqR2a","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3715,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3715,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01BGGboUGsf9nf4YB27kr1uD","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3715,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3715,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll rea"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll rea"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d the file first, then use multiedit to make both"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d the file first to see the exact content an"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" changes."} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d formatting."} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: content_block_start - data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01AapnpRtjkNBUeCvHjnfdmY","name":"view","input":{}}} + data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01Pd1MyYaE6kpBYnPGJ1Fy9p","name":"view","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"fi"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"file"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"le_path\""} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"_path\": \"/t"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":": \"/tmp"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"mp/c"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"/crush-tes"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"rush-test/T"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"t/TestCoder"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"estCo"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"Agent/anthr"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"derAgent/an"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"opic"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"thropi"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"-sonnet/mu"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"c-sonn"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ltied"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"et/multied"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"it_"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"it_tool"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"tool/main"}} + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"/mai"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":".go\"}"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"n.go\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":1 } + data: {"type":"content_block_stop","index":1 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3715,"cache_read_input_tokens":8770,"output_tokens":97} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3715,"cache_read_input_tokens":8757,"output_tokens":94}} event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.4692895s + duration: 3.268274625s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46491 + content_length: 46423 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first, then use multiedit to make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01AapnpRtjkNBUeCvHjnfdmY\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01AapnpRtjkNBUeCvHjnfdmY\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first to see the exact content and formatting.\",\"type\":\"text\"},{\"id\":\"toolu_01Pd1MyYaE6kpBYnPGJ1Fy9p\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Pd1MyYaE6kpBYnPGJ1Fy9p\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -185,139 +188,142 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01JCPycqpk75tvSFSdf7gJzU","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":161,"cache_read_input_tokens":12485,"cache_creation":{"ephemeral_5m_input_tokens":161,"ephemeral_1h_input_tokens":0},"output_tokens":37,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01G8qnsmV1nmWsKAnBETR9Yd","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":158,"cache_read_input_tokens":12472,"cache_creation":{"ephemeral_5m_input_tokens":158,"ephemeral_1h_input_tokens":0},"output_tokens":45,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_018wQtASDuqju9iJSKXDK8KX","name":"multiedit","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_018HUAoLFpcRazziegGrVwai","name":"multiedit","input":{}} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pa"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"th\": \"/tm"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"/t"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"p/cr"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mp"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush-test/T"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/crush-test/"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"estCoder"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"TestCoderAge"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Agen"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nt/anthrop"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/a"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ic-s"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nthropi"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"onnet/m"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c-sonne"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ult"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/multiedi"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ied"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t_"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"it_"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tool/"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"too"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main.go\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"l/main"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \""}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"edits\": [{"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"ed"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"old_strin"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"its\": "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"g\":\"func"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"[{\"old_str"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" main() {\\n"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing\":\"fun"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\tfmt"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c main() {\\"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".Println(\\\""}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\\tfmt.Prin"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Hell"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tln(\\\"Hel"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o, World!\\\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":")\\n}\",\""}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", World!"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"new"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\")\",\"ne"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_string\":"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"w_strin"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"f"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"g\":\"func"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"unc ma"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" main() {\\n\\"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"in() {\\n\\t//"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t// Gre"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" Gre"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"eting\\n\\t"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"eting\\n\\tfmt"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fmt"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".Println(\\"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".Println(\\\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"Hello, "}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Hel"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Crush!\\\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo, Crush!\\\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":")\\n}\"}"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":")\"}]}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"]}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":161,"cache_read_input_tokens":12485,"output_tokens":171} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":158,"cache_read_input_tokens":12472,"output_tokens":176} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.601883375s + duration: 4.754166792s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 47123 + content_length: 47061 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first, then use multiedit to make both changes.\",\"type\":\"text\"},{\"id\":\"toolu_01AapnpRtjkNBUeCvHjnfdmY\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01AapnpRtjkNBUeCvHjnfdmY\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_018wQtASDuqju9iJSKXDK8KX\",\"input\":{\"edits\":[{\"new_string\":\"func main() {\\n\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\"}],\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"multiedit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_018wQtASDuqju9iJSKXDK8KX\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first to see the exact content and formatting.\",\"type\":\"text\"},{\"id\":\"toolu_01Pd1MyYaE6kpBYnPGJ1Fy9p\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Pd1MyYaE6kpBYnPGJ1Fy9p\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_018HUAoLFpcRazziegGrVwai\",\"input\":{\"edits\":[{\"new_string\":\"func main() {\\n\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"}],\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\"},\"name\":\"multiedit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_018HUAoLFpcRazziegGrVwai\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -334,26 +340,26 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01MbTjyrGmAz9oHiX4CM1Dog","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":216,"cache_read_input_tokens":12646,"cache_creation":{"ephemeral_5m_input_tokens":216,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Pfg51VSKXmk7XDnb5LJxqi","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":221,"cache_read_input_tokens":12630,"cache_creation":{"ephemeral_5m_input_tokens":221,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":216,"cache_read_input_tokens":12646,"output_tokens":4} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":221,"cache_read_input_tokens":12630,"output_tokens":4}} event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.546877333s + duration: 3.260995042s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yaml index 5a875c5797f16ab35aa346d2cb7923a76f73d62c..0afc67508553cfb469c076f96cda33fd86cfb4e7 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/parallel_tool_calls.yaml @@ -25,49 +25,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01WUPzmEDtBzpSQ3zfN9YRNp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_017pT6NgbTzzXkCGSTQshTPp","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}} + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Parallel"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Parallel"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go File"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go File"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" an"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Discovery"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Directory Listing"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" and Listing"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":159,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 827.62075ms + duration: 563.628166ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45865 + content_length: 45798 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -84,61 +84,61 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_011d6o3Py5F1JwopexSMyXue","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3704,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_0194xppZMNBYpR4cTqu2EVf9","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3704,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01DRkMNp3tYzXDa937NtxkbX","name":"glob","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01RXPG7ekJ6r23yMpNyaWZ1T","name":"glob","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"patte"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"pa"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rn\": \"**/*.g"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ttern\": "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o\"}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"**/*.go\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: content_block_start - data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_0194t46qoBSpKXKewGWH8vZ6","name":"ls","input":{}} } + data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_019gc7awTgkJ8XcBF7L982ug","name":"ls","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"path\":"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"pat"} } event: content_block_delta - data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":" \".\"}"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"h\": \".\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":1 } + data: {"type":"content_block_stop","index":1 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8770,"output_tokens":86} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8757,"output_tokens":86} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.357026s + duration: 2.244434834s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46546 + content_length: 46479 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01DRkMNp3tYzXDa937NtxkbX\",\"input\":{\"pattern\":\"**/*.go\"},\"name\":\"glob\",\"type\":\"tool_use\"},{\"id\":\"toolu_0194t46qoBSpKXKewGWH8vZ6\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01DRkMNp3tYzXDa937NtxkbX\",\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"},{\"tool_use_id\":\"toolu_0194t46qoBSpKXKewGWH8vZ6\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01RXPG7ekJ6r23yMpNyaWZ1T\",\"input\":{\"pattern\":\"**/*.go\"},\"name\":\"glob\",\"type\":\"tool_use\"},{\"id\":\"toolu_019gc7awTgkJ8XcBF7L982ug\",\"input\":{\"path\":\".\"},\"name\":\"ls\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01RXPG7ekJ6r23yMpNyaWZ1T\",\"content\":[{\"text\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/main.go\",\"type\":\"text\"}],\"type\":\"tool_result\"},{\"tool_use_id\":\"toolu_019gc7awTgkJ8XcBF7L982ug\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\n- /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -155,38 +155,35 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01U615PD9vdshZjNp6yBpiWQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":12474,"cache_creation":{"ephemeral_5m_input_tokens":207,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Q7JbYpzEHTGw2DvPp1LDSQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":12461,"cache_creation":{"ephemeral_5m_input_tokens":207,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 1 Go file: `main.go`."} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d one Go file: `main.go`. Directory"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Directory contains `go.mod` and `main"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go`."} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" contains `go.mod` and `main.go`."} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":12474,"output_tokens":28} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":6,"cache_creation_input_tokens":207,"cache_read_input_tokens":12461,"output_tokens":26} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.502006s + duration: 3.10474175s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yaml index f120ce66e95bf69ba20d90a9c8af40d702d4f332..ade7ff4bc85fc86ad34b0ab53fd5edca359eb78b 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/read_a_file.yaml @@ -25,49 +25,46 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01LyHibm3ysLkpsN7aM5SmbR","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01FPxG45ganMpU7HdKFFJRAX","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Examine"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Rea"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d Go"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Module"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" File"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Mod Requirements"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":134,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":8} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 878.102292ms + duration: 675.620792ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45738 + content_length: 45671 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -84,73 +81,79 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01BHyBYhVXCpTBrWd3exLoyN","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3679,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3679,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_011vGHdc49fZFTncSji6gfpZ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3679,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3679,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01SsXtWbRtkvBPoBfzKhpn7p","name":"view","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_0127pa1AoNFjBcwBw4zYLKja","name":"view","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_path\": \"/tm"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_path\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"p/cr"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ush-tes"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"/tmp"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/T"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/crush-te"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"estCode"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"st/Test"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rAgent/anth"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Co"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rop"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"derA"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ic-sonnet/"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"gent/an"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"read_a_f"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"thropic-son"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ile/go."} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"net/read"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mod\"}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_a_fi"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"le/g"}} + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o.mod\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0} event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3679,"cache_read_input_tokens":8770,"output_tokens":79} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3679,"cache_read_input_tokens":8757,"output_tokens":79} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.701614584s + duration: 3.347076542s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46208 + content_length: 46141 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01SsXtWbRtkvBPoBfzKhpn7p\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file/go.mod\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SsXtWbRtkvBPoBfzKhpn7p\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Read the go mod\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_0127pa1AoNFjBcwBw4zYLKja\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file/go.mod\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_0127pa1AoNFjBcwBw4zYLKja\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -167,38 +170,35 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01TkUSeqWqeDQN2iQu5ZZLQf","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":12449,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_014d1eZhc3W5RKoHAvZuT7EP","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":12436,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}} + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Module"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Module"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":": example.com/testproject\nGo"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" is `example.com/testproject` on"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" version: 1.23\nNo"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" dependencies"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go 1.23, no dependencies."} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":12449,"output_tokens":22} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":12436,"output_tokens":23} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.6461245s + duration: 5.744573083s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yaml index 4f7c29fee74fe3d78d46d81214e48140464cabfa..ad2bdc2c2d582c840fd403b0c6ce394991a4d13e 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/simple_test.yaml @@ -25,46 +25,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_015TMuNhm2VpdL26vPjCVkGV","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01FA7ZZHsnXN3riuJK21jkFB","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}} event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Quick"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Quick"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Chat"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Hello"} } event: ping data: {"type": "ping"} - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Start"} } - event: content_block_stop - data: {"type":"content_block_stop","index":0} + data: {"type":"content_block_stop","index":0 } + + event: ping + data: {"type": "ping"} + + event: ping + data: {"type": "ping"} event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":6} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":131,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":5} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop"} headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.14484675s + duration: 567.335625ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45728 + content_length: 45661 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Hello\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"Hello\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -81,44 +84,29 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01DejF9BzDTMr861ivJgRgyQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":12444,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":12444,"ephemeral_1h_input_tokens":0},"output_tokens":8,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01GzNjpZKuLqwVRuTXLJWD9r","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3674,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3674,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello! I'm Crush, ready"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" to help you with your code"} } - - event: ping - data: {"type": "ping"} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello! How"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" and CLI tasks."} } - - event: ping - data: {"type": "ping"} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" can I help you today?"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } - - event: ping - data: {"type": "ping"} - - event: ping - data: {"type": "ping"} + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":12444,"cache_read_input_tokens":0,"output_tokens":21} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3674,"cache_read_input_tokens":8757,"output_tokens":12} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.45583075s + duration: 3.373099208s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yaml index f723d830a6bbb4aea755ad15d9df64d5a41e7539..44949ada65ec7db04853a1d8a95a6df86917e473 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/sourcegraph_tool.yaml @@ -25,46 +25,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01GytAqerXtvzEKHJJdSpnyY","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":4,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01DW7x9Bihrph6LzBucGdfeE","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":2,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Searching for main"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Search Go"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" functions"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Repos"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in Go repos"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" for Main"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Functions"}} event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":11}} + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 821.550416ms + duration: 537.344291ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45788 + content_length: 45721 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -81,47 +84,47 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01RZibC7Jyo5vQQk2nw4WJXh","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3690,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01GxPbWwzaww3bcLnXysTZi7","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3690,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01FVPtpkPPi1RXCDuKZ6E2ch","name":"sourcegraph","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01Fgv2C8Gdoym6CxBDEUR2FH","name":"sourcegraph","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"query\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"query\": \""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"lang"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lang:go fun"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":":go func "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c mai"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"co"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"count\": 1"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"unt\": 10}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"0}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8770,"output_tokens":74} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8757,"output_tokens":74} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.596813792s + duration: 4.503319375s - id: 2 request: proto: HTTP/1.1 @@ -143,21 +146,21 @@ interactions: proto_minor: 0 content_length: -1 uncompressed: true - body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":33,"offsetAndLengths":[[0,9]]},{"preview":"\tFuncA()","lineNumber":34,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncB()","lineNumber":35,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncC()","lineNumber":36,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncD()","lineNumber":37,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncE()","lineNumber":38,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncF()","lineNumber":39,"offsetAndLengths":[[1,4]]},{"preview":"func FuncE() {","lineNumber":4,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncE\")","lineNumber":5,"offsetAndLengths":[[14,4]]},{"preview":"func FuncD() {","lineNumber":8,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncE()","lineNumber":9,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncD\")","lineNumber":10,"offsetAndLengths":[[14,4]]},{"preview":"func FuncC() {","lineNumber":13,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncD()","lineNumber":14,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncC\")","lineNumber":15,"offsetAndLengths":[[14,4]]},{"preview":"func FuncB() {","lineNumber":18,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncC()","lineNumber":19,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncB\")","lineNumber":20,"offsetAndLengths":[[14,4]]},{"preview":"func FuncA() {","lineNumber":23,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncB()","lineNumber":24,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncA\")","lineNumber":25,"offsetAndLengths":[[14,4]]},{"preview":"func FuncF() {","lineNumber":28,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncF\")","lineNumber":29,"offsetAndLengths":[[14,4]]},{"preview":"\tFuncE()","lineNumber":30,"offsetAndLengths":[[1,4]]}]}]}}}}' + body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/01_before-func-expression/main.go","url":"/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/01_before-func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc greeting() {\n\tfmt.Println(\"Hello world!\")\n}\n\nfunc main() {\n\tgreeting()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":8,"offsetAndLengths":[[0,9]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]},{"preview":"func greeting() {","lineNumber":4,"offsetAndLengths":[[0,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/GoesToEleven/GolangTraining"},"file":{"path":"14_functions/10_func-expression/02_func-expression/main.go","url":"/github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/02_func-expression/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc main() {\n\n\tgreeting := func() {\n\t\tfmt.Println(\"Hello world!\")\n\t}\n\n\tgreeting()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":4,"offsetAndLengths":[[0,9]]},{"preview":"\tgreeting := func() {","lineNumber":6,"offsetAndLengths":[[13,4]]},{"preview":"package main","lineNumber":0,"offsetAndLengths":[[8,4]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":33,"offsetAndLengths":[[0,9]]},{"preview":"\tFuncA()","lineNumber":34,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncB()","lineNumber":35,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncC()","lineNumber":36,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncD()","lineNumber":37,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncE()","lineNumber":38,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncF()","lineNumber":39,"offsetAndLengths":[[1,4]]},{"preview":"func FuncE() {","lineNumber":4,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncE\")","lineNumber":5,"offsetAndLengths":[[14,4]]},{"preview":"func FuncD() {","lineNumber":8,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncE()","lineNumber":9,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncD\")","lineNumber":10,"offsetAndLengths":[[14,4]]},{"preview":"func FuncC() {","lineNumber":13,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncD()","lineNumber":14,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncC\")","lineNumber":15,"offsetAndLengths":[[14,4]]},{"preview":"func FuncB() {","lineNumber":18,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncC()","lineNumber":19,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncB\")","lineNumber":20,"offsetAndLengths":[[14,4]]},{"preview":"func FuncA() {","lineNumber":23,"offsetAndLengths":[[0,4],[5,4]]}]}]}}}}' headers: Content-Type: - application/json status: 200 OK code: 200 - duration: 1.384242041s + duration: 1.429988s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 53663 + content_length: 53517 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01FVPtpkPPi1RXCDuKZ6E2ch\",\"input\":{\"count\":10,\"query\":\"lang:go func main\"},\"name\":\"sourcegraph\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01FVPtpkPPi1RXCDuKZ6E2ch\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n```\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| \\tFuncB()\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n```\\n\\n```\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tfmt.Println(\\\"FuncA\\\")\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n```\\n\\n```\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| func FuncF() {\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n```\\n\\n```\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| \\tfmt.Println(\\\"FuncF\\\")\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n```\\n\\n```\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tFuncE()\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n```\\n\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use sourcegraph to search for 'func main' in Go repositories\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01Fgv2C8Gdoym6CxBDEUR2FH\",\"input\":{\"count\":10,\"query\":\"lang:go func main\"},\"name\":\"sourcegraph\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Fgv2C8Gdoym6CxBDEUR2FH\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| func main() {\\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func greeting() {\\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n## Result 2: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/02_func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/02_func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func main() {\\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\tgreeting := func() {\\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n```\\n\\n## Result 3: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -174,44 +177,44 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01Tu8fdNX66KN5a1WxY89Xtw","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":3890,"cache_read_input_tokens":12460,"cache_creation":{"ephemeral_5m_input_tokens":3890,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_014724o9o3akbVQp5S8V2bXU","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":3658,"cache_read_input_tokens":12447,"cache_creation":{"ephemeral_5m_input_tokens":3658,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Foun"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 30 matches for `func main` in"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d 30 matches for"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Go repositories. Example from github.com/jcalabro"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" `func main` in Go repositories. Results"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"/uscope shows a typical main function calling"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" include training examples from GolangTraining repository"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" various utility functions (FuncA through"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" showing basic main function usage an"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" FuncF)."}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d a backtrace testing program."} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":3890,"cache_read_input_tokens":12460,"output_tokens":50} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":3658,"cache_read_input_tokens":12447,"output_tokens":41} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.39525725s + duration: 2.144470791s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yaml index e8e3328269b1bb9c64481f188b6fa35d7acee40e..1195710a582adca3168b340107b1092f7729f24a 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/update_a_file.yaml @@ -25,49 +25,52 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_017uiUDrbzvGUvd5FsHWQvNi","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01W5jKwUPQD2FLMK2WSdGvHR","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Update"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Update"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Hello"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".go Hello"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Print"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" Print"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" in"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main.go"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 566.924ms + duration: 674.908625ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45794 + content_length: 45727 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -84,67 +87,94 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_0137dRq3tDoEShPFXEA3GGfR","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3690,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}} + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01B3DXnXZibVscXxLJhzYtgg","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3690,"ephemeral_1h_input_tokens":0},"output_tokens":3,"service_tier":"standard"}} } + + event: content_block_start + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"I'll rea"} } + + event: content_block_delta + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"d the file first to see its current content, then update it."} } + + event: ping + data: {"type": "ping"} + + event: content_block_stop + data: {"type":"content_block_stop","index":0 } + + event: ping + data: {"type": "ping"} event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01NSKz4J8fdHvbrDDMeEBHeP","name":"view","input":{}} } + data: {"type":"content_block_start","index":1,"content_block":{"type":"tool_use","id":"toolu_01SivyggTSfK7BShmdYXZnip","name":"view","input":{}} } + + event: ping + data: {"type": "ping"} + + event: content_block_delta + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":""} } + + event: content_block_delta + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"fi"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"le_pat"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"h\": \"/t"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_path\": \"/"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"mp/crush-"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tmp"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"test/TestCod"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/crus"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"erA"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h-test/TestC"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ge"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"oderAgent"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"nt/anthropi"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/anthr"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"c-so"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"opic-sonnet/"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"nnet/update_"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"update_a_fil"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"a_file"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"e/main.go\"}"} } + data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"/main.go\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":1 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8770,"output_tokens":79} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3690,"cache_read_input_tokens":8757,"output_tokens":96}} event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop"} headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.225666s + duration: 3.252981s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46338 + content_length: 46365 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01NSKz4J8fdHvbrDDMeEBHeP\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01NSKz4J8fdHvbrDDMeEBHeP\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first to see its current content, then update it.\",\"type\":\"text\"},{\"id\":\"toolu_01SivyggTSfK7BShmdYXZnip\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SivyggTSfK7BShmdYXZnip\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -161,133 +191,130 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01WoQ31LmNgHp2WFPXKKsdyQ","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":144,"cache_read_input_tokens":12460,"cache_creation":{"ephemeral_5m_input_tokens":144,"ephemeral_1h_input_tokens":0},"output_tokens":42,"service_tier":"standard"}}} + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01FrFSHBSdc8UAwrfb1knGDK","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":160,"cache_read_input_tokens":12447,"cache_creation":{"ephemeral_5m_input_tokens":160,"ephemeral_1h_input_tokens":0},"output_tokens":26,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_017ZZ3znMScoVDoGVPQ9eFiF","name":"edit","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01Y6UdvSDasvmGwtK5A5KNTe","name":"edit","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"fi"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"le_path\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"/tmp"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"/tm"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/cr"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"p/cru"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"us"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh-test/Test"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h-test/Te"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"CoderAgent"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stCode"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/anthrop"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rAgen"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ic-s"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/an"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"onn"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"thropic-sonn"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"et/update_a"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"et/upda"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"_file/main"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"te_a_f"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ile/main.go\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"o"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"old_stri"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ld_string\":"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ng\": "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \"func "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"func main"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"main() {\\n"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"()"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\tfmt.Prin"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" {\\n\\tfmt."} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tln(\\\"Hello,"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Println(\\\"He"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" Wor"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"llo"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ld!\\\")\\n"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", World!\\\")\\"} } - - event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"n}\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"}\""} } event: content_block_delta data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"new_st"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ring"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ring\": \"f"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"fun"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"unc"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"c main() "} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" main() "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\\n\\tfmt."}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\\n\\tfmt.Pri"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Pr"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntln("} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"intln(\\\"hel"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\"hel"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo fro"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo from "} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"m crush\\\")"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"crush\\"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\n}\"}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\")\\n}\"}"} } event: content_block_stop data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":144,"cache_read_input_tokens":12460,"output_tokens":147} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":160,"cache_read_input_tokens":12447,"output_tokens":147} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.709404666s + duration: 3.474816458s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46946 + content_length: 46973 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01NSKz4J8fdHvbrDDMeEBHeP\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01NSKz4J8fdHvbrDDMeEBHeP\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_017ZZ3znMScoVDoGVPQ9eFiF\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\",\"new_string\":\"func main() {\\n\\tfmt.Println(\\\"hello from crush\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"},\"name\":\"edit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_017ZZ3znMScoVDoGVPQ9eFiF\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"text\":\"I'll read the file first to see its current content, then update it.\",\"type\":\"text\"},{\"id\":\"toolu_01SivyggTSfK7BShmdYXZnip\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01SivyggTSfK7BShmdYXZnip\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01Y6UdvSDasvmGwtK5A5KNTe\",\"input\":{\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\",\"new_string\":\"func main() {\\n\\tfmt.Println(\\\"hello from crush\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"},\"name\":\"edit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01Y6UdvSDasvmGwtK5A5KNTe\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -304,26 +331,26 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_013EBTxE2pnbPMMaGR2iEFQv","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":199,"cache_read_input_tokens":12604,"cache_creation":{"ephemeral_5m_input_tokens":199,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01T8L3Lmwz5cHpp4sbtcZA1Z","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":199,"cache_read_input_tokens":12607,"cache_creation":{"ephemeral_5m_input_tokens":199,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":199,"cache_read_input_tokens":12604,"output_tokens":4} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":199,"cache_read_input_tokens":12607,"output_tokens":4} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.801013584s + duration: 3.310453041s diff --git a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yaml b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yaml index 42f1b14deef769026e939dd78e07b2dcac25f6bc..ac5714c0d4a0392a4ffed6268529b6960b469fa8 100644 --- a/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/anthropic-sonnet/write_tool.yaml @@ -25,49 +25,49 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_011unduGeE6BdA5baBxdT4HL","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01EygE1KGZz3X3ibj5Yf4RLN","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Create"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" config"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" config"} } event: ping data: {"type": "ping"} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".json with basic"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":".json with JSON"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" settings"}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" data"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} } + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":161,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":10} } event: message_stop - data: {"type":"message_stop"} + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 684.963041ms + duration: 574.209875ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45831 + content_length: 45764 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -84,97 +84,97 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01PAKKN2DTjjhxLWEttD3XC5","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8770,"cache_creation":{"ephemeral_5m_input_tokens":3704,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01U58TsX9NNkQuubNnpYnqqf","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8757,"cache_creation":{"ephemeral_5m_input_tokens":3704,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_01U9ettXkun9XrDjLEKvm972","name":"write","input":{}} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_015v3pfbXeD2N7WUz1d5Lkyj","name":"write","input":{}} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pat"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\": \"/"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": \"/tmp"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"tmp/cru"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/crush-test/"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"sh-t"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Te"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"est/TestC"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"stCoderAgent"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"oderAgent/a"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"/anthro"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nthropic-son"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"pic-sonne"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"net/wri"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"t/write_too"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"te_tool/con"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"l/con"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fig.js"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"fig.json\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"on\""}} + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"conte"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"c"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"nt\": \"{\\\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ontent\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"name\\\":"}} event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" \\"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\\\"name\\\": \\"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"test\\\", \\\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"test\\\", \\"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ve"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"versi"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rsion\\\": \\"} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"on\\\""} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"1.0."} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \\\"1.0.0"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"0\\\""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\"}\"}"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"}\"}"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8770,"output_tokens":109} } + data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":3704,"cache_read_input_tokens":8757,"output_tokens":109}} event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop"} headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.410829333s + duration: 3.586460958s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46400 + content_length: 46333 host: "" - body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_01U9ettXkun9XrDjLEKvm972\",\"input\":{\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\"},\"name\":\"write\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_01U9ettXkun9XrDjLEKvm972\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nFile successfully written: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\\n\\u003c/result\\u003e\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" + body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_015v3pfbXeD2N7WUz1d5Lkyj\",\"input\":{\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\"},\"name\":\"write\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_015v3pfbXeD2N7WUz1d5Lkyj\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nFile successfully written: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool/config.json\\n\\u003c/result\\u003e\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\u003c/communication_style\\u003e\\n\\n\\u003ccode_references\\u003e\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\u003c/code_references\\u003e\\n\\n\\u003cworkflow\\u003e\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\u003c/decision_making\\u003e\\n\\n\\u003ctask_scope\\u003e\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\u003c/task_scope\\u003e\\n\\n\\u003cediting_files\\u003e\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\u003c/editing_files\\u003e\\n\\n\\u003cwhitespace_and_exact_matching\\u003e\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\u003c/whitespace_and_exact_matching\\u003e\\n\\n\\u003cerror_handling\\u003e\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\u003cbash_commands\\u003e\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `\\u0026` for background processes that won't stop on their own (e.g., `node server.js \\u0026`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status \\u0026\\u0026 git diff HEAD \\u0026\\u0026 git log -n 3`)\\n\\u003c/bash_commands\\u003e\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\u003c/proactiveness\\u003e\\n\\n\\u003cfinal_answers\\u003e\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\u003c/final_answers\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"},\"name\":\"web_fetch\",\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\u003cusage\\u003e\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (\\u003e50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '\\u0026\\u0026', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in \\u003ccommit_analysis\\u003e tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n ## Summary\\n\\n \\u0026lt;1-3 bullet points\\u003e\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"name\":\"edit\",\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) \\u003e 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\u003c/examples\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"},\"name\":\"multiedit\",\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\u003c/operation\\u003e\\n\\n\\u003cinherited_rules\\u003e\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\u003c/inherited_rules\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\u003c/critical_requirements\\u003e\\n\\n\\u003cverification_before_using\\u003e\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\u003c/verification_before_using\\u003e\\n\\n\\u003cwarnings\\u003e\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\u003c/warnings\\u003e\\n\\n\\u003crecovery_steps\\u003e\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\u003c/recovery_steps\\u003e\\n\\n\\u003cbest_practices\\u003e\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\u003c/best_practices\\u003e\\n\\n\\u003cwhitespace_checklist\\u003e\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\u003c/whitespace_checklist\\u003e\\n\\n\\u003cexamples\\u003e\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}" headers: Accept: - application/json @@ -191,26 +191,26 @@ interactions: content_length: -1 body: |+ event: message_start - data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01187zADyPqje9k5UR4xo7uB","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":155,"cache_read_input_tokens":12474,"cache_creation":{"ephemeral_5m_input_tokens":155,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } + data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01KmBXvHhii6JTJQ1oVHtd64","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":4,"cache_creation_input_tokens":155,"cache_read_input_tokens":12461,"cache_creation":{"ephemeral_5m_input_tokens":155,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}} } event: content_block_start - data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } + data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""} } event: content_block_delta - data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } + data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"} } event: content_block_stop - data: {"type":"content_block_stop","index":0 } + data: {"type":"content_block_stop","index":0 } event: message_delta - data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":155,"cache_read_input_tokens":12474,"output_tokens":4}} + data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":4,"cache_creation_input_tokens":155,"cache_read_input_tokens":12461,"output_tokens":4} } event: message_stop - data: {"type":"message_stop" } + data: {"type":"message_stop" } headers: Content-Type: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.06819275s + duration: 5.472855042s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/bash_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/bash_tool.yaml index 090e4ad9a46a478f0fcbc93d20ac08af6923943d..8cb99f7734648bf7171256a53aef339e6afce2b4 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/bash_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/bash_tool.yaml @@ -24,25 +24,27 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"xeE0RFXRxxO55q"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pGHQqD7nA6xClq"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Creating"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"cgSejht8"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"TU3FQzFuok"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"bqgG6kba7Zjm6b"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"jOCPOsaRvNw"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"YecbiX7fxXv"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" test"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"dskt2DKShr2"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"b72NKAWSgv7"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":".txt"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"YQ0VBHokFitf"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"aHXRi22C"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rU4NO4nlo8t"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"5QnS7kDWcT"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IUUse6Cjpj"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Bash"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"XQEKqn4AFg9"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Bash"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Vk3KtkrYm5U"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"EIvpqD2Mwv"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"tgSwhxTx"} - data: {"id":"chatcmpl-CVGgw7EnMqgImV3IRSsBOkqHvrLyx","object":"chat.completion.chunk","created":1761568366,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":7,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"HTwltwCinqzkvH"} + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"rO8vPwWjhX"} + + data: {"id":"chatcmpl-CVfMXnD4YmHCkrpioDkYdzv2CtlTy","object":"chat.completion.chunk","created":1761663201,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":8,"total_tokens":147,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"LKNzTKqrDa3ziJ"} data: [DONE] @@ -51,15 +53,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 472.351333ms + duration: 571.266458ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44232 + content_length: 44160 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -75,144 +77,103 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_bzXhjhzb4yTTT13dmQGZK531","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"f1AxMnni1D58"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_erkF6IfOlov2o4mh61BZURul","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"8AI10ylDQr9A"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"4OoIPPxCFmZQdZr"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lyLjYLsah3knXhL"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Vxt7jWmXnJg"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7E0UBWSHDVr"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"B1S4GF7RarX9z"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"v6zLCNQL4MvKd"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"printf"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wzj2c6tfcv1H"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"printf"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CyG9VaqwdO3q"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qHtCuOfGamqQF"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BgFO6h569qqt9"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"x46lFuq3Pn1YC"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oMYv0D4W0ADFi"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"'"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"'"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" >"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" >"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Sgsix7LyJwlHc"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LcY0ZDT3AR0edd"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TbzR8EYrqTNUP6X"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"gntZwFfKQwjTj"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GH7ddrVAERhBi5P"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cjFcCly"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zHIfsxnoYmjFQ9k"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"HwW2CYPuP8CBk"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0O517MLyFMXSJ"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Create"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Nc1B4d1Zmwaq"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7gtyTGhkfrZgv"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M9N8wDy3P3h20"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GJewD53oV6g34"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8mhHLl3KMS4yD1"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gfCv9U0AKE7An"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" with"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rZYYcquuBcU27"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cOfbsrqjbCfAU"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" exact"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BeWf4ieOmOAl"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gUo6pPq09B"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" without"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UB15sDI0K2"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" trailing"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kr6HDT3lr"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" newline"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iZWxvpzBU2"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"BFJPTQ7b3jPADaa"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nD0PCY5PoVWB0"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GT2kKFX9Ne7VF"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z7qgNBhw3fKZY"} - data: {"id":"chatcmpl-CVGgwV22dOB3tsiJUVGIL0AYmuUpT","object":"chat.completion.chunk","created":1761568366,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9741,"completion_tokens":619,"total_tokens":10360,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DC01jBstBSEuRx"} - data: [DONE] + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"MgH6wO5V1n9Co"} - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 10.709038375s -- id: 2 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 44581 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_bzXhjhzb4yTTT13dmQGZK531\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"printf 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt with exact content without trailing newline.\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_bzXhjhzb4yTTT13dmQGZK531\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.openai.com/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_rGK0OEyaogLnoF0NPTrmlOSM","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"kHgCRIbexqDg"} - - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"uunjOVfyZAPdvHs"} - - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H3YWGiH082kuX1"} - - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jfa2adn5sMQUN"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OTGLras"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qi7BqS3u1UV1WJ4"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"E1Lzhc4GMdyKz"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LibXt4sT7Phc7ui"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Create"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0SdJupVSMKXt"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YilWZriO1koyNVF"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DW0cr4FA5o6wM"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nTM6oK1ZI8U95CJ"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jynRiI0IbTKIWR"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QWQEdYTkvZmxjMM"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" with"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oSGTE4PDlGmtd"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UYjVoDEp8eiZf"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" exact"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fjoMXLtKriJk"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ytZsaB0JBYIjb"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oKmM5lpLa8"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1eFGsmY8UyDTC"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" '"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GaEvD7x9OCvJX"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CkVI3wuKAcSUz"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vsfMfP0lLRlNj"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VzNpQDZ0CsP3O"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"'"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" ("}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"no"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" trailing"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6z6Lo34EB"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"W"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" newline"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xLaDSMcyHP"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/bash"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RkBbaSnYRxkkB"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":")."}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QLBCOzN3eYx8K"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fNdVcyiq90IVgF5"} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SB5BbqNbstkUu"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"byxNFFb7HANUxI"} - - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BhVv3E2s5tflsNM"} - - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGh7WqVoUnKM8HBw7GRpqwdzop3Z","object":"chat.completion.chunk","created":1761568377,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9790,"completion_tokens":232,"total_tokens":10022,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"jlS"} + data: {"id":"chatcmpl-CVfMYBUnIg1xyd3Kt2QgwTKWEaqKF","object":"chat.completion.chunk","created":1761663202,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9744,"completion_tokens":576,"total_tokens":10320,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":512,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} data: [DONE] @@ -221,15 +182,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 6.4291665s -- id: 3 + duration: 11.110321292s +- id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44910 + content_length: 44573 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_bzXhjhzb4yTTT13dmQGZK531\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"printf 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt with exact content without trailing newline.\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_bzXhjhzb4yTTT13dmQGZK531\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_rGK0OEyaogLnoF0NPTrmlOSM\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/test.txt\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|hello bash\\n\\n\",\"tool_call_id\":\"call_rGK0OEyaogLnoF0NPTrmlOSM\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_erkF6IfOlov2o4mh61BZURul\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"printf 'hello bash' > /tmp/crush-test/TestCoderAgent/openai-gpt-5/bash_tool/test.txt\\\",\\\"description\\\":\\\"Create test.txt with exact content 'hello bash' (no trailing newline).\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_erkF6IfOlov2o4mh61BZURul\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -245,13 +206,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhEkVvjL8ihoTO4aL3qGYuWO5ww","object":"chat.completion.chunk","created":1761568384,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"PLri6M5gNV"} + data: {"id":"chatcmpl-CVfMjv9q58WKu4LWz0oTmThQWAGGy","object":"chat.completion.chunk","created":1761663213,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"QTabRIJUa4"} - data: {"id":"chatcmpl-CVGhEkVvjL8ihoTO4aL3qGYuWO5ww","object":"chat.completion.chunk","created":1761568384,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"sQbjMbPz"} + data: {"id":"chatcmpl-CVfMjv9q58WKu4LWz0oTmThQWAGGy","object":"chat.completion.chunk","created":1761663213,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"PYS3PVfl"} - data: {"id":"chatcmpl-CVGhEkVvjL8ihoTO4aL3qGYuWO5ww","object":"chat.completion.chunk","created":1761568384,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"D7jNvW"} + data: {"id":"chatcmpl-CVfMjv9q58WKu4LWz0oTmThQWAGGy","object":"chat.completion.chunk","created":1761663213,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"adTrxF"} - data: {"id":"chatcmpl-CVGhEkVvjL8ihoTO4aL3qGYuWO5ww","object":"chat.completion.chunk","created":1761568384,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9847,"completion_tokens":4,"total_tokens":9851,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"24vQx"} + data: {"id":"chatcmpl-CVfMjv9q58WKu4LWz0oTmThQWAGGy","object":"chat.completion.chunk","created":1761663213,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9814,"completion_tokens":4,"total_tokens":9818,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Oc3H7"} data: [DONE] @@ -260,4 +221,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.52050775s + duration: 1.639221417s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/download_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/download_tool.yaml index 21b0981364beb9a4007783cd2f2dab20af018381..f1914d3c051b057e494dcdba60c8b911d4bdea5b 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/download_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/download_tool.yaml @@ -24,23 +24,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4QHabbGK6DjmzQ"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ahfxGvHErD1qIt"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Download"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"coOtETsj"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Download"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"jDkgqHhd"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"gF9Cc0sX92ke"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MhAVGcg6FiAo"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Save"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sH2XMaxQwyH"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Save"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"aQ4XugXWHQ2"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Example"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"S2u9pOyT"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ttJfW3jOBhc"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Text"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"CbyaZmOloQu"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" from"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WU6XYRsVeuQ"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"28jhPEbqYhZ"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" URL"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"h6pKez6HGVw2"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"si1kJlCIWU"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Example"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"eAMtRY5u"} - data: {"id":"chatcmpl-CVGhFH8lxWxXLxqDY58ODKarEzqKy","object":"chat.completion.chunk","created":1761568385,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":148,"completion_tokens":6,"total_tokens":154,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"jgKacbi7oLSzdQ"} + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"bS7B6xPAWS"} + + data: {"id":"chatcmpl-CVfMlcprQyIALVRXktkMgoAgnHvJS","object":"chat.completion.chunk","created":1761663215,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":148,"completion_tokens":7,"total_tokens":155,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"0PqKx2wuUpgKHz"} data: [DONE] @@ -49,15 +51,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 454.701458ms + duration: 603.351125ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44285 + content_length: 44213 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -73,97 +75,97 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_9foyvevwEwCyxR3CPKSsnI5p","type":"function","function":{"name":"download","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"RT5j5lk3"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_HXGiXrTSOjMiG74Jp0oqHzex","type":"function","function":{"name":"download","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"pf3y1VLy"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"9g1NyivrrnuUrXG"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"wtSNo1MTFuBHHz3"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8JeQI76ulOXIO5"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qUeV6qi8FsW6vf"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yaEh9dJbfPtAx"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3CgaCEYVT4jmH"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uJmmirKBuq2ps5x"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5mp1SUOLhhffFTc"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Nnun80VBYEcdOWJ"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yXXWbjA7T2jk2WC"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8PVBubb7scyHV7c"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ibDRB2oQKhRNNji"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Fvenm7D9HEPuqj0"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uKuumgc0eKr3tBL"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YGqGLUIL3Vs7ksS"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Dsc03o1mbPl9L6t"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CYT0mOWoIIJcw"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3OAwP0V3ujSMf"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PvsDn6FeHHCbV"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ucAk1sr7Bv6pS"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2u9ApakJr2X80"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uTT7C79pgfEuz"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZODS6iRYwRyt6"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hi3iLAsGexuDa"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JvfS1jGZiDUog"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FVm0JT3iwk8o6"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"U"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/download"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rRf9JrI7o"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/download"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UNK4aq2jr"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qPdsIwQT9WmJb"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"og4gDdwC5cR1J"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZST4v60iBW"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0lZOdbBYKU"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SwjdZF3eMl6jq6"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TNNtvYASbmnjrX"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"y1aMMBDHENDYu"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"C31rFHmwlp0UL"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ukpN5M3H9MRRc8D"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tzF0RIgh2DyV0E5"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Pe2naqESHDbfx"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"dUKYRfsD7SLRq"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JgMnWKIIFCkOE"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"x25HICOCEsj2B"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7JppNJnyXDaMDU7"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KpPttUhCdDvY645"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gp5kHnTq84u"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LXcmgpxveaH"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QdwvMA8x73fR"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FCx9vTM0j6mu"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nOYT7n3BU5u"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aYCxalKiiuD"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-con"}}]},"finish_reason":null}],"usage":null,"obfuscation":"djgHZ6AoP7x5mR"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-con"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FZuHPu4oCdmvrr"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"vert"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nM3IGkyuEzQw4N"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"vert"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GY7ActYZG5hmhu"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".com"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hqVv1s1RU0ihCh"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".com"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PVtNGKWUYik2aP"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/document"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GD8runY1z"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/document"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I18AWfJ9K"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/t"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/t"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"xt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"xt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KYDKUZ2Sap"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Nfx8aiIDzI"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jFxFtufAw0hwux"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".txt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"npa7Rq5ZkbZlKU"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"HWKC1qdVkqZka"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"bps5wkvSEb1EJ"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"t1hgfhuRAn1"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QH6s86TdiYJ"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uCQWnrOrFAkrYc4"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zBQQJbbazCC6Wbe"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"120"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qc7VwDA1bp4A0nf"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"120"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N0aBgv89DFj3rSW"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M"} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j"} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhF6xDcfsPVamlcBiG8PqbqwGEN","object":"chat.completion.chunk","created":1761568385,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9749,"completion_tokens":380,"total_tokens":10129,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfMl5qA9JKKhCkF0d5TgKzGzT2oR","object":"chat.completion.chunk","created":1761663215,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9752,"completion_tokens":316,"total_tokens":10068,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} data: [DONE] @@ -172,7 +174,7 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 7.729834958s + duration: 7.383364042s - id: 2 request: proto: HTTP/1.1 @@ -218,15 +220,15 @@ interactions: - text/plain; charset=UTF-8 status: 200 OK code: 200 - duration: 86.009166ms + duration: 136.773459ms - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44832 + content_length: 44760 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_9foyvevwEwCyxR3CPKSsnI5p\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool/example.txt\\\",\\\"url\\\":\\\"https://example-files.online-convert.com/document/txt/example.txt\\\",\\\"timeout\\\":120}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_9foyvevwEwCyxR3CPKSsnI5p\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_HXGiXrTSOjMiG74Jp0oqHzex\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool/example.txt\\\",\\\"url\\\":\\\"https://example-files.online-convert.com/document/txt/example.txt\\\",\\\"timeout\\\":120}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/openai-gpt-5/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_HXGiXrTSOjMiG74Jp0oqHzex\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -242,13 +244,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhNgBxeYK3gifDE7ZdxX0hdrPHM","object":"chat.completion.chunk","created":1761568393,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"LKQFFpd3lI"} + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"yL8zjfSPVO"} + + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Saved"},"finish_reason":null}],"usage":null,"obfuscation":"Hdz16XI"} + + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" to"},"finish_reason":null}],"usage":null,"obfuscation":"ci3kMjZpB"} + + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}],"usage":null,"obfuscation":"DyRk"} - data: {"id":"chatcmpl-CVGhNgBxeYK3gifDE7ZdxX0hdrPHM","object":"chat.completion.chunk","created":1761568393,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"EoHFfBbm"} + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".txt"},"finish_reason":null}],"usage":null,"obfuscation":"mVmXzeW8"} - data: {"id":"chatcmpl-CVGhNgBxeYK3gifDE7ZdxX0hdrPHM","object":"chat.completion.chunk","created":1761568393,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"RGBUS4"} + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"VWGH2J"} - data: {"id":"chatcmpl-CVGhNgBxeYK3gifDE7ZdxX0hdrPHM","object":"chat.completion.chunk","created":1761568393,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9850,"completion_tokens":4,"total_tokens":9854,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"uBrQM"} + data: {"id":"chatcmpl-CVfMtftzW0MAM08U2NaPw9vsH9dy8","object":"chat.completion.chunk","created":1761663223,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9853,"completion_tokens":7,"total_tokens":9860,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"NeSTD"} data: [DONE] @@ -257,4 +265,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.323540792s + duration: 2.38613725s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/fetch_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/fetch_tool.yaml deleted file mode 100644 index b22f739f32c3b93f76913e8db62de9f535b61ec1..0000000000000000000000000000000000000000 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/fetch_tool.yaml +++ /dev/null @@ -1,255 +0,0 @@ ---- -version: 2 -interactions: -- id: 0 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 794 - host: "" - body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nfetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word ''John Doe''\n \n\n","role":"user"}],"model":"gpt-4o","max_tokens":40,"stream_options":{"include_usage":true},"stream":true}' - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.openai.com/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"daVnpgPm4VmR7B"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Check"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Mg3MvWaG76d"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VwkfaVdl3z9Y"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"JdN1PE3S5FXm3t"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"John"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4CCiMjneah7e"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Doe"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7NTt4Yvg1D2c"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HkXpfCTvuVl2pNc"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"m9DReCKdlNvWp"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Website"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Kd9GrIrH"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"lx9dGCom"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Qtc6CmsT1o"} - - data: {"id":"chatcmpl-CVGhPuALM21rTRM7PcoObvpGZgohg","object":"chat.completion.chunk","created":1761568395,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":153,"completion_tokens":9,"total_tokens":162,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"GHzJW3rpScLqX6"} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 467.236ms -- id: 1 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 44303 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.openai.com/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_XBp2OyMczTXPWXjjixioGvfO","type":"function","function":{"name":"fetch","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"Xz1FKfSFDGU"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Vlvh1tIh5Axd6Dr"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"url"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HBIWw1WpnVHesQ6"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ajf0gLsjFK4t0"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"https"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RKZ02ryWhlMMY"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"://"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Eg1SI0v9dJc18JH"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FXXE3gRki0V"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-files"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jDwkk8AH0Ur6"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".online"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lDVEuVgHt1k"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-con"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2bukPvvEeZsp1y"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"vert"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nPmBMxSkaszUan"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".com"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tiq9aWZxHOCkW5"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"website"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3pvW3eGLPez"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/html"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gdyMFek7e8ibl"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/example"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cAWD9SjvOT"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".html"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VYspwbSGRBrL6"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"24mY0dXckipAN"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"format"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1LcEmQ6nId4A"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"jISsjctkXik7W"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iLcspRo1QzUO6Y"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"SEawlU3k5jzGn"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HOZE0ePfDL5"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NiBrN0B52KHvdIb"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGhQkieUke92QaxIzSWVagaUK1a8","object":"chat.completion.chunk","created":1761568396,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9756,"completion_tokens":170,"total_tokens":9926,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"r"} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 3.216805167s -- id: 2 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 0 - host: example-files.online-convert.com - headers: - User-Agent: - - crush/1.0 - url: https://example-files.online-convert.com/website/html/example.html - method: GET - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - uncompressed: true - body: |- - - - - - -

HTML test file

- -

Purpose: Provide example of this file type
- Document file type: HTML
- Version: 1.0
- Remark:

- -

- - Example content:
- The names "John Doe" for males, "Jane Doe" or "Jane Roe" for females, or "Jonnie Doe" and "Janie Doe" for children, or just "Doe" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.

- -

John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series.

- -

Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases.

- -

- - File created by https://www.online-convert.com
- More example files: https://www.online-convert.com/file-type
- Text of "Example content": Wikipedia
- License: Attribution-ShareAlike 3.0 Unported - -

- -

Feel free to use and share the file according to license above.

- - - - headers: - Content-Type: - - text/html; charset=UTF-8 - status: 200 OK - code: 200 - duration: 49.594958ms -- id: 3 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 47135 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_XBp2OyMczTXPWXjjixioGvfO\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://example-files.online-convert.com/website/html/example.html\\\",\\\"format\\\":\\\"text\\\",\\\"timeout\\\":60}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"HTML test file Purpose: Provide example of this file type Document file type: HTML Version: 1.0 Remark: Example content: The names \\\"John Doe\\\" for males, \\\"Jane Doe\\\" or \\\"Jane Roe\\\" for females, or \\\"Jonnie Doe\\\" and \\\"Janie Doe\\\" for children, or just \\\"Doe\\\" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of \\\"John Doe\\\" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand. John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series. Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, \\\"John Doe v. Jane Roe\\\". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) \\\"John Doe\\\"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases. File created by https://www.online-convert.com More example files: https://www.online-convert.com/file-type Text of \\\"Example content\\\": Wikipedia License: Attribution-ShareAlike 3.0 Unported Feel free to use and share the file according to license above.\",\"tool_call_id\":\"call_XBp2OyMczTXPWXjjixioGvfO\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.openai.com/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"chatcmpl-CVGhTCKneAAOPxLAAYnq6kJxKyS2j","object":"chat.completion.chunk","created":1761568399,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"6raqEIh7rF"} - - data: {"id":"chatcmpl-CVGhTCKneAAOPxLAAYnq6kJxKyS2j","object":"chat.completion.chunk","created":1761568399,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Yes"},"finish_reason":null}],"usage":null,"obfuscation":"eLwKExFNF"} - - data: {"id":"chatcmpl-CVGhTCKneAAOPxLAAYnq6kJxKyS2j","object":"chat.completion.chunk","created":1761568399,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"3bH3aP"} - - data: {"id":"chatcmpl-CVGhTCKneAAOPxLAAYnq6kJxKyS2j","object":"chat.completion.chunk","created":1761568399,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10350,"completion_tokens":138,"total_tokens":10488,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"OL0f7af4M7TLQtn"} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 4.971612125s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/glob_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/glob_tool.yaml index 192f67086eb7fb02f5f081a44313a2fb93d694f5..ab1b96f1b30e135908ad5b8463e2dc1a3c2492e6 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/glob_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/glob_tool.yaml @@ -24,29 +24,29 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8jgsvvnWfkWFyo"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VdRj2QwhmU7ylH"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Finding"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Y6d3F70UA"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Finding"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"C4EScgKIl"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" ."},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rHONqHy6BbmtbU"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" ."},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1g1no7aoF1lit0"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"5GlwsFjPubzbBn"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Nw1FvrTnPnF2ll"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"wciSGQi9QH"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"1krebXYUh1"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sG5AX8fYNC6"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"SFb7m1CZGJTq9"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"FnSrmXBHQnT"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Current"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"dAiDQ8tR"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7O9XexmyzCGCg"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Directory"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"07u1V1"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Current"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"aylb4NNf"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WYSkQQpiPVu"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Directory"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HCktzv"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"nNMNWG4alcm"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"IhEHGfQ0jl"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"BgkEiRn2hp"} - data: {"id":"chatcmpl-CVGhYvOetx4fuImilVyL6dWeEWRLC","object":"chat.completion.chunk","created":1761568404,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":137,"completion_tokens":9,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"BaC1XCxBGlLeEW"} + data: {"id":"chatcmpl-CVfN4pzznFb333KUwRukm5TGHmkJ0","object":"chat.completion.chunk","created":1761663234,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":137,"completion_tokens":9,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Mrdw9wkK9yzDx0"} data: [DONE] @@ -55,15 +55,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 492.080083ms + duration: 602.034667ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44221 + content_length: 44149 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -79,23 +79,23 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_PMj4cFe1yLgB5XYfN5XXwoUe","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"wVDfmu9hGyn1"} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_seU3vSJ9Yo8NZXxqRfQulHrr","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"drKrcoH3xMiJ"} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"awwD1AIeU4bQx53"} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"OssHoGVhB2TLywv"} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JnZTjD3opCp"} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A6GHaBDw70F"} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"KOWt1z26BYI3s"} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"gIfVwYgAE1ptF"} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LpXsb8pmEAYbnNw"} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CfLeBQuYNbO9VxN"} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhYeozrjkISWJAmUBLdgwR3vRDx","object":"chat.completion.chunk","created":1761568404,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9739,"completion_tokens":87,"total_tokens":9826,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"GAC"} + data: {"id":"chatcmpl-CVfN5JCQ3mJbIuT5TtwRWxkxdHFYL","object":"chat.completion.chunk","created":1761663235,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9742,"completion_tokens":87,"total_tokens":9829,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"57smxl"} data: [DONE] @@ -104,15 +104,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.61713075s + duration: 3.828790041s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44515 + content_length: 44443 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_PMj4cFe1yLgB5XYfN5XXwoUe\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool/main.go\",\"tool_call_id\":\"call_PMj4cFe1yLgB5XYfN5XXwoUe\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_seU3vSJ9Yo8NZXxqRfQulHrr\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/glob_tool/main.go\",\"tool_call_id\":\"call_seU3vSJ9Yo8NZXxqRfQulHrr\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -128,49 +128,49 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"UT6NJkhDaz"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"9O3A8fJ9O1"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"IbhbZeGvz5L"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"8h7MEBbUkqF"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"EJqskqtDx"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"9TAvMlT1m"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"l221tBBcF"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"HchdihQ87"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"ZmhxRR6JV"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"XhEIvLIFX"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"EddJgDO"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"ecXr2Zv"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"Zedu768"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"BRsuYYS"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"avCaHnz"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"jYApV9X"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"zzD3zCy"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"FVK87Vp"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"cUUBCpc"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"q35DSKS"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"vy4ndGx5l7"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"R6v9kM9Sey"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"nDw9iXXiSf"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"zcXUCaflFS"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"zYzJPt1d49"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"v3O7TS6ITN"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"xb67kmjpxZE"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"HutD9ycN83B"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"WJFi64lo4xx"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"M5DpwBWwonx"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/gl"},"finish_reason":null}],"usage":null,"obfuscation":"JiPzqKUV0"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/gl"},"finish_reason":null}],"usage":null,"obfuscation":"BFnTTLMQb"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ob"},"finish_reason":null}],"usage":null,"obfuscation":"PBcJm2mglX"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ob"},"finish_reason":null}],"usage":null,"obfuscation":"4TIyMhb1pI"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"M542K60"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"e8FTZmU"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"b2KlBLj"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"cOj2vOV"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"veGWruw1R"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"2aGZFSY12"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"JTB4Ux"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"bfGIgE"} - data: {"id":"chatcmpl-CVGhbIO5ASq33C3foer7Gu5RQJU5w","object":"chat.completion.chunk","created":1761568407,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9784,"completion_tokens":22,"total_tokens":9806,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"d9JQ"} + data: {"id":"chatcmpl-CVfN8ZnNwFvSVbado9rW4SPqEMbsV","object":"chat.completion.chunk","created":1761663238,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9787,"completion_tokens":22,"total_tokens":9809,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"nKE5"} data: [DONE] @@ -179,4 +179,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 895.840417ms + duration: 1.663874667s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/grep_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/grep_tool.yaml index 6ef68b5502287333c130e81e7b764757f0fc5f02..57ad846aaa320001fbf799f86981ed7b900be35e 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/grep_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/grep_tool.yaml @@ -24,31 +24,31 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WMfgWjD9b4iboA"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"uXg68pOTl3PHAu"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Search"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ISDGMho3Un"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Searching"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"nvKUZDn"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"eVSBw2NEMvHs"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"LR1rPzLCwejn"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"kWRALmg09l0feY"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ydrFFJHYPHERIG"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"package"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Qmc7wOPOw"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"package"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"s8VQ3GK11"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ceGaOGVIPpVreHS"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0v5a1A9LGYQ72oi"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"BMIfRzXwpMDVy"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"z1k9cJQ5P8NAx"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"wTmsx9mk1TlJi"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ek1lU1KOtB4IU"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"S1J7O84ihu"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"jZt2RbFyNS"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"UCcyS79ip7"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"X2tWIoxtnF"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" grep"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MsGm3j68Uns"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" grep"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"BNYVfD20VtX"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"Dlv6SEJZZe"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"t4C3bCA3xf"} - data: {"id":"chatcmpl-CVGhcAVHb35eOkzllQyaarsJHQRRM","object":"chat.completion.chunk","created":1761568408,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":10,"total_tokens":148,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"537NaK1vnhWQ7"} + data: {"id":"chatcmpl-CVfNBlhP8asPAxxVynV8y1PPY3nsu","object":"chat.completion.chunk","created":1761663241,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":10,"total_tokens":148,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"0xwaEcHF5c6ez"} data: [DONE] @@ -57,15 +57,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 398.25575ms + duration: 644.30575ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44219 + content_length: 44147 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -81,41 +81,41 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_pMdnjgWimteNRV4Aa062xYnU","type":"function","function":{"name":"grep","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"OkyhFloHWB7Z"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_wgKdeovcswRIXePACmqckpL3","type":"function","function":{"name":"grep","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"Fwz2WK7dDw6W"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"0pdmFV89Lu1oziO"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tM0SoPeUFHUIjRY"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"include"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xyz90r2t5IL"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tUteBt2lsMp"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"MGp8FAKMVjHIc"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"K87SL16j5kcfN"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}],"usage":null,"obfuscation":"prpzfYQJUdM"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"aOaQa0PaCKmsi"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"zB5lwrZF3YKfU"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"include"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QvqZBgSGwB9"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"literal"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CouR2BCkMj1"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"AFdQtUUpJRALT"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HFcc52ktL4otF"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"*."}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9KrWnmiXkfGcrWB"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"true"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sz8HmhUovHou5B"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"IsYwnccgGvYVh"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"TdXeWFjJwCaeCAU"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"literal"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hwLubgKPQit"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FTnU4fpWw7z"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_text"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gDZSg7Pvjy73B"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"k20a3d0zyXJvV"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"D0hX8DAPA3sZNBx"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oxJff8rzwWP"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"true"}}]},"finish_reason":null}],"usage":null,"obfuscation":"voSAO26GUSxMpU"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qQTn8XtBY4UK1Uz"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P"} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhceklAbxIw5LaiietJToNyfLb7","object":"chat.completion.chunk","created":1761568408,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9740,"completion_tokens":225,"total_tokens":9965,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"8"} + data: {"id":"chatcmpl-CVfNBc0TDWVkw8Go9MSyubBcQxXfj","object":"chat.completion.chunk","created":1761663241,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9743,"completion_tokens":225,"total_tokens":9968,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"H"} data: [DONE] @@ -124,15 +124,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 4.226984709s + duration: 3.6056395s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44611 + content_length: 44539 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pMdnjgWimteNRV4Aa062xYnU\",\"function\":{\"arguments\":\"{\\\"include\\\":\\\"*.go\\\",\\\"literal_text\\\":true,\\\"pattern\\\":\\\"package\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_pMdnjgWimteNRV4Aa062xYnU\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_wgKdeovcswRIXePACmqckpL3\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"package\\\",\\\"include\\\":\\\"*.go\\\",\\\"literal_text\\\":true}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_wgKdeovcswRIXePACmqckpL3\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -148,61 +148,63 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"Sgujh7usF1"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"HOGYv1OVnU"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"sACMeCEQxxy"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"FCb8uPehGGm"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"16xdVrrp3"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"uve4jDrxL"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"XLIqnpYgR"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"mFvJgSRFh"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"uFAyc44Er"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"zOIvf9jS3"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"K7aj2lN"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"wFQ7Ryg"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"uDdSJwN"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"0KRUBRG"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"b51Vrgo"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"HotTBIk"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"EHElaV5"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"4oNviqb"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"5cMQ9kg"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"BlXYurf"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"Ccvd20e0Ha"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"jCUgapiZ4f"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"cygX91cb0L"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"YePsk60wTH"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"GS6wWwtX6N"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"2ns7OkymlN"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"unB2GcKmDCB"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"5rumsvWDy1d"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"ywKbdCpdL7i"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"rGWmHJ3xpee"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"pVcxXjOYtoV"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"qQP0roMhXqa"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"grep"},"finish_reason":null}],"usage":null,"obfuscation":"DgDSz4Fa"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"grep"},"finish_reason":null}],"usage":null,"obfuscation":"AEUSrE2n"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"0OJtVxD"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"h3vRUpH"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"e52UaGz"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"sPT4DeG"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"6lO9IH73V"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"aRmU0Ai7v"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"ZuWQNIyTdUL"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"APv5jwHmaF3"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"GUFvRTaOS5o"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"llXJIMJTcqF"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"DbZYNfvXPuo"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"xl8ZBUmdhYv"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"Q4pVlbwFAOP"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"z0pxvrQWXbr"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" package"},"finish_reason":null}],"usage":null,"obfuscation":"wREn"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"T97KtlywbVG"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"4N97Q1f"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" package"},"finish_reason":null}],"usage":null,"obfuscation":"deN5"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"9okJBS"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"YjlMy9W"} - data: {"id":"chatcmpl-CVGhgBFX0IrSHbMBPff4HBXION4Ks","object":"chat.completion.chunk","created":1761568412,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9813,"completion_tokens":28,"total_tokens":9841,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"xIGc"} + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"a0Blok"} + + data: {"id":"chatcmpl-CVfNFvfHLLsLYFXtbsOHKiwN7DYs2","object":"chat.completion.chunk","created":1761663245,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9816,"completion_tokens":29,"total_tokens":9845,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"2e2R"} data: [DONE] @@ -211,4 +213,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.27848275s + duration: 2.415104709s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/ls_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/ls_tool.yaml index 204a6ebc0c47f8ef770bf044b49c5694a39a15c8..eed52ec950ed064fda2ac19ccd4ca48a26b637b2 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/ls_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/ls_tool.yaml @@ -24,21 +24,27 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"xOBWtkw676hxWd"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"yeVbLsn0KSfT9A"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"List"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QNax3zNXou2U"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Listing"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"HdY0E3Ldb"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Uwb07Q74LB"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Files"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"w69gt8VUsl"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"3lyChTLFVw9"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"mLypgnOvOoH"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" LS"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"wm9yf3iMXBldO"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" the"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"xFUxzyiq5Pe8"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Command"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"xfnGgqY4"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VszhbgLYgsCso1"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"FZkAxIrL1f"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"ls"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"SMM88sffvdcVCV"} - data: {"id":"chatcmpl-CVGhi7Jyhoss9Dn7fKn3WhVJcS8r7","object":"chat.completion.chunk","created":1761568414,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":135,"completion_tokens":5,"total_tokens":140,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"lfFIBahqXvb3hZ"} + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2u9Uj0ZgM9LEE2z"} + + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Command"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IWzDxfqt"} + + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"wScu5JD1yH"} + + data: {"id":"chatcmpl-CVfNIb8BlKZf39oxwxfCKy481Iozr","object":"chat.completion.chunk","created":1761663248,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":135,"completion_tokens":8,"total_tokens":143,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Scr3c5WYWwoc8v"} data: [DONE] @@ -47,15 +53,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 369.083375ms + duration: 577.433417ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44213 + content_length: 44141 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,29 +77,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_v0ol3iLROSuEYhgJqgJNWgpr","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"bJjukLFpmh763E"} - - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"nYe8iejyiTHppKE"} - - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pVaecfQkrdQXoy"} - - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hcjnKYsu0LST1Vl"} - - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"Lp83skhnBQzj6Xb"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_tsUghih6YJiT7VDMjcKKymFu","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"6bfZOIowgje9BC"} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"wcWWYB2NmHL3u"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"GoItwxJsnUXqO4H"} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5cM02lbpwZr7S"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OCYtCse7uz45Qh"} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5F0xJW9iRtGfz9e"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wMw0zcdvnGXkO8s"} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \".\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hXEQ6F4YyxrR"} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"F"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhi3h5nL9r2h6b6SKTxpj3Nq2z4","object":"chat.completion.chunk","created":1761568414,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9737,"completion_tokens":155,"total_tokens":9892,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"a"} + data: {"id":"chatcmpl-CVfNIW4BWNW8k0ptxWXv4mVlAgDq0","object":"chat.completion.chunk","created":1761663248,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9740,"completion_tokens":215,"total_tokens":9955,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"i"} data: [DONE] @@ -102,15 +100,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 4.547614125s + duration: 4.924636s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44533 + content_length: 44450 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_v0ol3iLROSuEYhgJqgJNWgpr\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\".\\\",\\\"depth\\\":1}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_v0ol3iLROSuEYhgJqgJNWgpr\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_tsUghih6YJiT7VDMjcKKymFu\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\".\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_tsUghih6YJiT7VDMjcKKymFu\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -126,21 +124,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"EpVpo8btm6"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"WTdxs8UUMN"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"JUL094UyXp"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"a6on38LjPj"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"NYCI3pMb"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"CJ8t7UFQ"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"finish_reason":null}],"usage":null,"obfuscation":"aTrNVC9pJbF"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"finish_reason":null}],"usage":null,"obfuscation":"PODmRDaYJJn"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"qNiABVj"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"B5K4ItU"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"Q3DcGrsjJ"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"AX2ULhcFw"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"lrMqpo"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"aqVOUD"} - data: {"id":"chatcmpl-CVGhmOXvgGfJnijCIZTMF9sASNz38","object":"chat.completion.chunk","created":1761568418,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9798,"completion_tokens":8,"total_tokens":9806,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"SImtv"} + data: {"id":"chatcmpl-CVfNNT2rvCBxu9dLkmLQK2LPPRtkc","object":"chat.completion.chunk","created":1761663253,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9797,"completion_tokens":8,"total_tokens":9805,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Rjc1W"} data: [DONE] @@ -149,4 +147,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 4.192681375s + duration: 2.170903042s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/multiedit_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/multiedit_tool.yaml index 31bda5f784bb75191f1f6a59233327e2ae193079..612d39d3224e7dbee4ab349505ccbabd2b3ef702 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/multiedit_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/multiedit_tool.yaml @@ -24,41 +24,31 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"5gkEgWjVTOTnSL"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ZGGEAO7nAiRHuY"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Editing"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MJZGSrCzh"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Edit"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sGVUVk17GWiV"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ltbJ0K1ZnvBT2D"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4EjiKJ0CABCD"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VUqmP0WPp25"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Comment"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"59fun9hp"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"foPXZoVvjJKtuGi"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"lbifuILM5ZlOF"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" World"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"idwQToDE9N"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Eantz1xKbD7"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"!'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"gk6ZAJROv7rnrl"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sg13lSyn4a1HI"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2ZBbXXBj0bMlP"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Using"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"cTsgnTqcac"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"hXlZ1hGxiN5qAG"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Mult"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"bEHC2WPeTO9"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"v8WgKqzNTnK"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"ied"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"e0gNGHeQXHLxM"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9NcEasUlux5vRzJ"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"it"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"5U5ntmSTK5VYeB"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Crush"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9JNKf9qEar"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"6WmumR0z8U"} - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"!'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"yzlrO15jy63gQI"} - - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"5kd6G2rJg7wxq"} - - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"SSJtEfm08MA"} - - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"CdqyTSYSbWOhl"} - - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"IC4DFCRQ5M"} - - data: {"id":"chatcmpl-CVGhq42hILaUefpj0DqO1tqILLmD1","object":"chat.completion.chunk","created":1761568422,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":157,"completion_tokens":15,"total_tokens":172,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"bfvjwG8g2WIVE"} + data: {"id":"chatcmpl-CVfNPVIBrpBNuB2oGNCxrKbRgYnGx","object":"chat.completion.chunk","created":1761663255,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":157,"completion_tokens":10,"total_tokens":167,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"mu62hWyLhZ6Da"} data: [DONE] @@ -67,15 +57,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 450.499625ms + duration: 579.264458ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44299 + content_length: 44227 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -91,69 +81,71 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_M8JMNgXyJ8mrhOIoIZ9yI5R6","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"G9yeKSsvPFYLCB"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_JlXpqBYdqtlfFG5JZWSEbRoo","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"jeDpgg7JqGS2"} + + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"TcarHRjfkvaWplL"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"pagy052CNzmoKXM"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IjGeesFYp2o"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yOJyYPqvHIHP6w"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"VqQPszhCmMnwZ"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BOabhX52TSqh6M9"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"**"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LjsqN2sINRf3GZ"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gIC1VRUlp3PN2a0"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ASOlLmbsY5VnYK"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tpz4KiogARqYeZ4"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mSVPQxJv9jPP2RZ"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lLt92aBIW0gtINg"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ej1da6Fxh7WOk"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"trXINW52mrqim"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RRrHKkNfGXKBYW"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ebhvc8dWP43t2"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"a7tD8w6LAkv6T9K"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bDUEz2JmJXjix"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WwaT90mMiFFlSHi"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jA4WzI8MyMWzF"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kdgdacukmOhti9w"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"R60qO94DrdVxB"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A81oMVS4x1kZwbk"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YFrALp0x2OkAUAc"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N2PCUSmuRkxLX"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZxV6XGBIr3SmS"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pTBAkA5hEG3GU"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nbri29P8fjIhx"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1GA8IinOzah1P"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5dw9euZNn0pvJm7"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Grevk5hspDUTHRe"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"420qeDucuATu4"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"yFWaaCPggSUsqhF"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"zFv1Jc6DqdxgGpW"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FvigcIAAH1cJj"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YQ0UJhsJ9zGSOBO"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ekYHFrbDSCbYlCA"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I8ESlLUtoaRixWT"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Rpf9bMjlKs81q"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iDNMB0dCMtyF7kQ"} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhrfSlUUkKWyLJnJBrEYy9OT266","object":"chat.completion.chunk","created":1761568423,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9761,"completion_tokens":175,"total_tokens":9936,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"G"} + data: {"id":"chatcmpl-CVfNPqT4CapZVYABcDi4KD5r9fPGq","object":"chat.completion.chunk","created":1761663255,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9764,"completion_tokens":239,"total_tokens":10003,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} data: [DONE] @@ -162,15 +154,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.232691916s + duration: 5.525106542s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44686 + content_length: 44604 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\",\"tool_call_id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -186,73 +178,63 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_uGv7TR5OUgNcVFHd4Ooqr0i2","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"APL8JdRNaCTf"} - - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"bsk0ftM7vEyAlhA"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_p6iPAE1CcqORgJwTF1Mh2Dgd","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"jjmu6PrFEiyQ"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VqwYd7xUPxnJYL"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"sIuWWD7xnN4KxEC"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hZKPWR7Q7tRSy"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fAWAcit4x2bhSK"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BKbeUFD7lnFxN5M"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EqYkwd3s55dYw"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KEV6ThuKGeenh8r"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tl1DhkVrFvzC9o4"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FAp5Qu4KIqFfBd2"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X76YJ2pOPIUfUKJ"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ifvGnULLocNRHeg"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"grePMfsmAiOi771"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HhuxBSYAXKF57Fp"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QQ0gQgZqyQGbO3o"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ct54Rz0heYXyC"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"km2hvGj9Q9QjrFf"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dumJ9EvUDtYfc"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TBKhn6qnBWWFe"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UvA6OKXqbMyoJ"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j7asDWoJ1OCmz"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hvcIPUxyQzGcw"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oVOXIxyTwMg9G"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qojxcywm7PR9v"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pcT5Xbx8e2ujA"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CofgSEjYFf1kj"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DAPAH14TJUfF44o"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NOgJFgBn4FyAnlP"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5DrVvcdEmjfoRLr"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wZWEuZsVmYH44WA"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZstspVBleDtrU"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UaAfYI9o8DtSZ"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s8Zi861tTLffM"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OLV9WhnIxQHgSvE"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bWlYT1HBQ9yvO"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"HYjIsd2Um9cng"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FBtypgddGjjAgHT"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"limit"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lJy6ogGMLIXWo"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"79f3zVUFc8xJXRK"} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CrLWQzSOybkwXlR"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"200"}}]},"finish_reason":null}],"usage":null,"obfuscation":"edz4E1fz6pEk0Ev"} - - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3"} - - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"} - - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGhuaNHEeXUTVXLbv2naHsXltHHd","object":"chat.completion.chunk","created":1761568426,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9842,"completion_tokens":42,"total_tokens":9884,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"KL6r"} + data: {"id":"chatcmpl-CVfNVhpSrhVD8WOz1zWcQVMhbWxdZ","object":"chat.completion.chunk","created":1761663261,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9835,"completion_tokens":37,"total_tokens":9872,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"3omf"} data: [DONE] @@ -261,15 +243,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.33445925s + duration: 1.654741541s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45150 + content_length: 45053 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_uGv7TR5OUgNcVFHd4Ooqr0i2\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"limit\\\":2000}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_uGv7TR5OUgNcVFHd4Ooqr0i2\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\",\"tool_call_id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_p6iPAE1CcqORgJwTF1Mh2Dgd\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_p6iPAE1CcqORgJwTF1Mh2Dgd\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -285,193 +267,249 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_n31l0pRhqRYfHYrig7M5LxBI","type":"function","function":{"name":"multiedit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"Lhoe1CZ"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_gk3SQodQcQC8MDUFYDdkM7yt","type":"function","function":{"name":"multiedit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"nEwWlNQ"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"0cbDlZ2mWzhyVEs"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8E0Ks0oveoqx3u"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oOUkt6Hw8nE65"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yfBTGfWr5olw2xZ"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QEsFw4WYvUGwQ7B"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0oCMAZ2r5LSNnXw"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zWupvZlSMZSh5np"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wcnyCSrw7BIUXu3"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eU4Ae5fz1AYSK"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s5BchkOk8Rz5Z"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"W7alXmjA9LEcg"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pxsHHEAeJGZT6"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oFDsWcd72QaUy"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"QbkzjsfawWXN6s6"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V4rj8QvO9CFsFm"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"41SdkD36s8lpa"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CMViUUKnIdYxLm6"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BvXAGX7jLWb4eCF"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jVT1kVtdUXGlwSi"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KOSzSXeML7MbTGE"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nCH4xWx1117m5it"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HMtQyP7STKESx"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bz3jOusNGuEVgXA"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YcqJKTPyNiq8y"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hSDp2H4rXUSp5d8"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FPTRXxPBE5zsiuo"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tibOz4ps2L15A"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Yb18vqSRxCm3X"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6u5nAhH7CWvqP"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ed"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aRFWuKWEV4zme"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"its"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nHumwWA4ROcp798"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nglNAuizfrUL1"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":["}}]},"finish_reason":null}],"usage":null,"obfuscation":"nOppAspyNSO82m"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PXqorKEPDsjJ2"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ksmc9adshdMNfCu"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5u5C0mRDSwvrxrT"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ySqQg5KsWTd"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"gCWZl4whFcbLj"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4PAc9PmdrL9Lux"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BTz4dxsV7Vhbi"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ha7w8RruyeTYGXw"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XocRUmhqthBiVL"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e7TdXbXAYjAfuPt"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o1DiUHciG2T1eQC"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7GVvzwK9fBfNc"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eKsgwL2fiVzasWM"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m6zdQjLx3NZiq"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"krA1yyHNC4"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"v6HMKJp8LAgyAIE"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"WYRa8D3h01MU3"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"CmrVK4eEbfGka"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X3P7S7baA3UO7"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ed"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"R"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"its"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QXbx1a4t0KaQ1vq"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Bb7UofoLIOXu"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":["}}]},"finish_reason":null}],"usage":null,"obfuscation":"TT014z3eHKwCXF"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MVsiOAM0f67cdq9"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"AnujHPL9i7YrSbX"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZajvVid7X9YmDYH"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C2jTtvsvljAYUrm"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NhfMNkWK3Gc"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"cZYi9SaVDlQLF"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"fyitZ3w42ankY"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tf"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HHVTBbLt5OoVxvo"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"mt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"p0L1c0IarUy"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IU8Og9hBUK"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PAp6lx2rek6zB"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"O9iIG3xiMnyVV"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"du4CdqeiqtrDvI"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xJjjhKNf6NyNg"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q9DuLY8uZNRNx"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"V"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dpzNtDXTvvSw"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jp9yJMsVZ2wDPD"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V25t2VKO1TNjQYi"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"u"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vrNF9C5tcBEDvuC"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YaoU2Q6jof9aLjH"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PFfLIslI6AeBh"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2XswdGuCLc1C5fJ"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0sDepLnE1tbEGWJ"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"biaKkLVqsl"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zY5N5hYzGDZ"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"4xq9vmZ7bwN51"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"o4Uchvn0yoyBd"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9oz8jToT0RM1N"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"j"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GUcrt13ezosZ"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"//"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IuyH6t1GFsjXRul"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Greeting"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zvHPNCK7b"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gIEbPPmD9ZECFWG"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qolRcs0LTK52qZx"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UzC9OrC91NNrZdu"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l686OKgPh3IMTZS"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"iPksClRJqxBXPzZ"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hXk1TJI9VZ"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"},{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"eY7UWUhtjikXS"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PUTgSNaP3QI7F"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qIX6YgJQtw7Ig9L"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IusYoTiTen198"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pNxsYoyso9C"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"a"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"lSzDeIeAC7oo6"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iip0dIXk5oam"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B0knH923ENgZPH"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"k3VvAtMsl6fExHq"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hpTi3LwE2bak8"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6ghgjiMRQx41vxR"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"},{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"rnSNHmcOxgk"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xviaCpyxsm2AhU"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CfopYctXqGGLJQC"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2FDx82Nd0bn"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JwXoYcYB7A3LFeR"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"YFElPKwFWGxjt"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iUmoCUUAdG3zrAD"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"E9h9lsjr2E"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"668J3EjLctBny"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FbdrOWieGckDSe7"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GWad1gEDsQu1N"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VlMvWls3c3"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"t"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"GNnM0cZcacrcJ"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l5TPF0aGMNvh"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UtPoZ4qxNLaMn"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n3ALEOBbEstZsBb"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"S"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"i4458JWvxpwM7U2"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EMmGwq2bYTrj"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m8QuvGrYmErVTTS"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m34HrunJdAKsN31"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"oS8J4nWypiIcm"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"uGVxcZ8yeh9oS"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bU4jRGgOojfxRwv"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ewOtulq0ie14PKH"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Zpmjyd3Nwwh"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"trOL3fSGcPt"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"R3i3XPfV5UC1W"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PdaVDZXJpEAUv"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"D6oxJqh3R78b50"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"u"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UUwtcBQsJeaKg"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QP3kWJh0IK3CIim"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ft4kmEQmpi"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RoxrLNFJGTLpWf"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"QFLVomFKo0Q1B"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G0ibO5bEah2KK"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Aslx97CUjqZFK39"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"X"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"//"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xPbQoicAoSYM"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Greeting"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WP5GERDPM"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FA1ZZI0FgBsZHD0"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4ZWcGx7ZJbmQUfr"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BrVNiJp8N6cAf7K"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"READJK2WzE8XNZH"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vSAfgRs8qNEUlOK"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aHIz4r9vmQ3c45t"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"]}"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HhEgP6PMNd"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"7uO9fycDO5jUD"} - data: {"id":"chatcmpl-CVGhwdsPo3rwbcg0nn7oWLpc6mxv7","object":"chat.completion.chunk","created":1761568428,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9946,"completion_tokens":1134,"total_tokens":11080,"prompt_tokens_details":{"cached_tokens":9856,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":1024,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"xCLdn2O05CnUXt"} + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q8GNVvwX0kPtr"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d5lrz1uT94BJ"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nvXeVFGYGw1CcyO"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Dt9M5YiRN6Sa5wZ"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YzADHJiJzja3AAs"} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"]}"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfNXiasfeuZbVoYiQ2lzBllbF4qM","object":"chat.completion.chunk","created":1761663263,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9934,"completion_tokens":1418,"total_tokens":11352,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":1280,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Xce1Ce7OwKQfUF"} data: [DONE] @@ -480,15 +518,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 17.4236815s + duration: 19.061113s - id: 4 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45827 + content_length: 45810 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_uGv7TR5OUgNcVFHd4Ooqr0i2\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"limit\\\":2000}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_uGv7TR5OUgNcVFHd4Ooqr0i2\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_n31l0pRhqRYfHYrig7M5LxBI\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"},{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"call_n31l0pRhqRYfHYrig7M5LxBI\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\",\"tool_call_id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_p6iPAE1CcqORgJwTF1Mh2Dgd\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_p6iPAE1CcqORgJwTF1Mh2Dgd\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_gk3SQodQcQC8MDUFYDdkM7yt\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"},{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"call_gk3SQodQcQC8MDUFYDdkM7yt\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -504,97 +542,63 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_nKIH0obmQeaPNpjqK1OVYIbF","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"uK5LeD11s7pz"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"cZdJCSkheNxD6uH"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"87P5buAM0CF"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ObOJCpUwj5UC8"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"S04cWQiHqf410Z"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3Uw8iwIMZiQBzQD"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cdjJgvNwjCCqAul"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"St5GSyr1EqdoEST"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qw54ZdTtjZiO9"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4Rb8zOlWcMoQO"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gVl2P9U2FpiPL"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WseDP1vHY2jaU"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4H9hcoPNPBY6T"} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_l8oMEvpMDIkvfbAq584WE9ir","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"rW9MkXvx5IBv"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"p"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Fx32KCOEpfbrfBq"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jwNf5YVfLW0Kae"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L6LKuS9tjHaeZ"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KHGk8vx6sD5ztaO"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GmP6Pa5hE9EV221"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dEeaI8DRY1p5mI7"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8RFM3CyUSPJbgrY"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"86w2pHHiU99mfl8"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eDvP6AXzoi57K"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fZNCAJGcM0wsaCx"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uG04bCtJccwUN"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LVxYghdhlUr7xn3"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M0jFB3Sa6ptXFge"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bMErdGJuKUHhi"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"PPFAWbkmJetTL"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gBY12OWT0wGhP"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5OirQDk"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JsmNfEMFZzDNg"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tBPPyztbvPF8t"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"i98bUt7VO0zcD"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3Gj8TWQTPPIuNEL"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2rI4IznK84NSF"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AO5RxZUvF0FKFC"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"osEci644vza8lhC"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" program"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3IVTU0LLg9"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" to"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6XDb31mEzlgOYd5"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"g"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" ensure"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L4HDfCr6wUC"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" it"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ezGvn5eLZTKomtp"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/m"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" builds"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rQw3dasOTZY"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ult"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T1pugjo0yoW79om"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" and"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IlN6U4lKFTeOwA"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ied"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B412ahFdNadpuIn"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" outputs"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C49KqFLIe9"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"it"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hpGyEvc1BaLuDj"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rktwoRNCemTw9"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dPXGPaYsjK7gfx"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bUiMNBVTf8DqL"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" greeting"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B91CibE0J"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nD2n2ftIfIvCk12"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hyCGj16KrwA9Ive"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zi7nQJOKwTQEBOB"} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiD1IH2rr5SJocPUyOxrMEvCNje","object":"chat.completion.chunk","created":1761568445,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10097,"completion_tokens":55,"total_tokens":10152,"prompt_tokens_details":{"cached_tokens":9856,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Fn"} + data: {"id":"chatcmpl-CVfNqlPoG29jxLwuoTgBGbRzMUkIO","object":"chat.completion.chunk","created":1761663282,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10113,"completion_tokens":37,"total_tokens":10150,"prompt_tokens_details":{"cached_tokens":9856,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"XN"} data: [DONE] @@ -603,15 +607,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.55581425s + duration: 2.360623791s - id: 5 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46305 + content_length: 46281 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_M8JMNgXyJ8mrhOIoIZ9yI5R6\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_uGv7TR5OUgNcVFHd4Ooqr0i2\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"limit\\\":2000}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_uGv7TR5OUgNcVFHd4Ooqr0i2\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_n31l0pRhqRYfHYrig7M5LxBI\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"},{\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"call_n31l0pRhqRYfHYrig7M5LxBI\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_nKIH0obmQeaPNpjqK1OVYIbF\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"description\\\":\\\"Run the Go program to ensure it builds and outputs the new greeting\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Hello, Crush!\\n\\n\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\",\"tool_call_id\":\"call_nKIH0obmQeaPNpjqK1OVYIbF\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\",\"tool_call_id\":\"call_JlXpqBYdqtlfFG5JZWSEbRoo\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_p6iPAE1CcqORgJwTF1Mh2Dgd\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_p6iPAE1CcqORgJwTF1Mh2Dgd\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_gk3SQodQcQC8MDUFYDdkM7yt\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"},{\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 2 edits to file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"call_gk3SQodQcQC8MDUFYDdkM7yt\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_l8oMEvpMDIkvfbAq584WE9ir\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\t// Greeting\\n 7|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 8|}\\n\\n\",\"tool_call_id\":\"call_l8oMEvpMDIkvfbAq584WE9ir\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -627,13 +631,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGiFMc1sBiTI94g9A6VS5YqgVVeE","object":"chat.completion.chunk","created":1761568447,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"FK4KqLSLV0"} + data: {"id":"chatcmpl-CVfNtMFbX4cARf3xcr574GO7qSdd2","object":"chat.completion.chunk","created":1761663285,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"VKW7nvRB4s"} - data: {"id":"chatcmpl-CVGiFMc1sBiTI94g9A6VS5YqgVVeE","object":"chat.completion.chunk","created":1761568447,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"herNBb6M"} + data: {"id":"chatcmpl-CVfNtMFbX4cARf3xcr574GO7qSdd2","object":"chat.completion.chunk","created":1761663285,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"MKpjWixw"} - data: {"id":"chatcmpl-CVGiFMc1sBiTI94g9A6VS5YqgVVeE","object":"chat.completion.chunk","created":1761568447,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"twXMFj"} + data: {"id":"chatcmpl-CVfNtMFbX4cARf3xcr574GO7qSdd2","object":"chat.completion.chunk","created":1761663285,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"W8obSE"} - data: {"id":"chatcmpl-CVGiFMc1sBiTI94g9A6VS5YqgVVeE","object":"chat.completion.chunk","created":1761568447,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10190,"completion_tokens":4,"total_tokens":10194,"prompt_tokens_details":{"cached_tokens":10112,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Ib"} + data: {"id":"chatcmpl-CVfNtMFbX4cARf3xcr574GO7qSdd2","object":"chat.completion.chunk","created":1761663285,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10220,"completion_tokens":4,"total_tokens":10224,"prompt_tokens_details":{"cached_tokens":9856,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"hrL"} data: [DONE] @@ -642,4 +646,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 883.650375ms + duration: 1.797561042s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/parallel_tool_calls.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/parallel_tool_calls.yaml index e831c1a5da2283b2b19fc54df8a6faeeea544e06..b9c7f635f4819509a3cf6481c17d8017186e9fc5 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/parallel_tool_calls.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/parallel_tool_calls.yaml @@ -24,27 +24,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"a4aeRi5yFSlp0I"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"eDZ2GmsL0XZzjl"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Run"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"t2xAJAB6ghrBG"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Parallel"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0zbJiurp"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4pCqp3PwUND"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Execution"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pmCgRZ"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2kaRZRnwpUAe"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" of"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"71IAMyDPt4LQD"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" List"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"DGlQBn5dN0d"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Glob"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"uHKoUxHcjHH"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Directory"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"qA6cbc"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" and"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"DKep9MJQK5dr"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Commands"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2T7v8NG"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" LS"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"RxV0Npzrs9qH4"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"YNcH8yF2P72JO"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Commands"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"UYQTC5Y"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Parallel"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"FeNGcH6"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"XaRIJd8GS0"} - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"7kjQteMuZa"} - - data: {"id":"chatcmpl-CVGitmInvDHUk3ghtpsrmlVjuVGTU","object":"chat.completion.chunk","created":1761568487,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":154,"completion_tokens":8,"total_tokens":162,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"FeAhrzodraw7Ux"} + data: {"id":"chatcmpl-CVfOXTNvCUoluDkZN5qO600nXHLey","object":"chat.completion.chunk","created":1761663325,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":154,"completion_tokens":7,"total_tokens":161,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"cbGRSghi3E0d9n"} data: [DONE] @@ -53,15 +51,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 540.224584ms + duration: 527.81725ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44310 + content_length: 44238 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -77,27 +75,27 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null},"finish_reason":null}],"obfuscation":"7406Pcu"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null},"finish_reason":null}],"obfuscation":"m7u9gSj"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_l1FwLeFqzftQzEqkZz0ezU62","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null}],"obfuscation":"7ymRsnqZAqUnZ"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"call_KLsrLCnMM6u74bT9W7WCIgaU","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null}],"obfuscation":"EbnzqbgYPn2zf"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"bWFlV8L1ZVcam"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\"pa"}}]},"finish_reason":null}],"obfuscation":"17YfLPTJUxt2y"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ttern"}}]},"finish_reason":null}],"obfuscation":"D1ACL76ZZBwum"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ttern"}}]},"finish_reason":null}],"obfuscation":"uEaC428qeRoug"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\": \"**"}}]},"finish_reason":null}],"obfuscation":"QV3SnroUOb"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\": \"**"}}]},"finish_reason":null}],"obfuscation":"Uwi6huVU1z"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/*.g"}}]},"finish_reason":null}],"obfuscation":"HXlZoaSacEZyBi"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/*.g"}}]},"finish_reason":null}],"obfuscation":"qsVqADeeBvI5xF"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"o\"}"}}]},"finish_reason":null}],"obfuscation":"zU7MLG9QQJGzPb"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"o\"}"}}]},"finish_reason":null}],"obfuscation":"dw2h11MZ5WPkQW"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"id":"call_H8zbI2ej4BsxZC7ibiuEfTHw","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null}],"obfuscation":"0WCMX7vYZBavgyp"} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"id":"call_OT0z1UrQtlHXxf4NV8d5ceZ1","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null}],"obfuscation":"DtGabOoBmLeoQmO"} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{}"}}]},"finish_reason":null}],"obfuscation":""} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"usage":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":1,"function":{"arguments":"{}"}}]},"finish_reason":null}],"obfuscation":""} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGitGjNHyd2fDgmfxphfGzdFvKbB","object":"chat.completion.chunk","created":1761568487,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9757,"completion_tokens":372,"total_tokens":10129,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfOYjxGJ85OgTdnjRdJKEpnxBtNc","object":"chat.completion.chunk","created":1761663326,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9760,"completion_tokens":244,"total_tokens":10004,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":192,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} data: [DONE] @@ -106,15 +104,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 6.987463167s + duration: 6.797483917s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44888 + content_length: 44816 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_l1FwLeFqzftQzEqkZz0ezU62\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_H8zbI2ej4BsxZC7ibiuEfTHw\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_l1FwLeFqzftQzEqkZz0ezU62\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_H8zbI2ej4BsxZC7ibiuEfTHw\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_KLsrLCnMM6u74bT9W7WCIgaU\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_OT0z1UrQtlHXxf4NV8d5ceZ1\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_KLsrLCnMM6u74bT9W7WCIgaU\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_OT0z1UrQtlHXxf4NV8d5ceZ1\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -130,111 +128,65 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"GcglGBUMFJ"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"dDaddE97cgr"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"i2jwWtqSr"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"ztGNCKZOM"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"KQeM07boc"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"GZIFL1D"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"yhm8U7s"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"1HxF9Pr"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"REaDu8c"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"iBThLi4"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"NwsogZMZwi"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"oLN4aznapk"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"iLYRwvs91z"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"Zh84WB8aUiz"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"Vq0ecY7qhPK"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"8bHVimRTb9j"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"parallel"},"finish_reason":null}],"usage":null,"obfuscation":"PhBe"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"uH7ER1N"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_calls"},"finish_reason":null}],"usage":null,"obfuscation":"MCYHVF"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"AZ2X0hG"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"5Ru9TNkH0"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n\n"},"finish_reason":null}],"usage":null,"obfuscation":"doTFxlfY"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"oEjOCt5ToFa"} - - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" /"},"finish_reason":null}],"usage":null,"obfuscation":"6xUVMBS5rJ"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"VU9wD8UXaE"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"OSVmFXf3J"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"I4bfvdisUAi"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"gNOIfRZry"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" /"},"finish_reason":null}],"usage":null,"obfuscation":"pHk5PZhtLS"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"vMScb1ICX"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tmp"},"finish_reason":null}],"usage":null,"obfuscation":"OG2cSaX5C"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"yPq3CdT"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/cr"},"finish_reason":null}],"usage":null,"obfuscation":"PsgvlTxP7"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"0f1J7So"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ush"},"finish_reason":null}],"usage":null,"obfuscation":"azGyI2lDH"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"RKN0uNY"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-test"},"finish_reason":null}],"usage":null,"obfuscation":"t8bSyzp"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"a1CDvAj"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/Test"},"finish_reason":null}],"usage":null,"obfuscation":"7ej6Ukz"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"NyOG8vc"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Coder"},"finish_reason":null}],"usage":null,"obfuscation":"yHd8E23"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"ZqyPAb53Do"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Agent"},"finish_reason":null}],"usage":null,"obfuscation":"NJfQ1hb"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"t3o2WuaMpM"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/open"},"finish_reason":null}],"usage":null,"obfuscation":"7b2QtHC"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"v1LuiqaO64"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ai"},"finish_reason":null}],"usage":null,"obfuscation":"ciiaqLM1sa"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"pHQ6jANOTm3"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-g"},"finish_reason":null}],"usage":null,"obfuscation":"wO3l4I91ap"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"NyZFRjoik0Y"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"pt"},"finish_reason":null}],"usage":null,"obfuscation":"22o6Q4st5T"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"GO4W73R2JpG"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"am3A78PQPcH"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"parallel"},"finish_reason":null}],"usage":null,"obfuscation":"KXfl"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"um7cCn2SXC6"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"XZp3BwT"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"U6RYu3qkS5J"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_calls"},"finish_reason":null}],"usage":null,"obfuscation":"gTh0Lz"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"parallel"},"finish_reason":null}],"usage":null,"obfuscation":"yzxH"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/\n"},"finish_reason":null}],"usage":null,"obfuscation":"IkFgtY1g2"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tool"},"finish_reason":null}],"usage":null,"obfuscation":"7T30AxA"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"cTwc8tlJuvs"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_calls"},"finish_reason":null}],"usage":null,"obfuscation":"EeKAzY"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"lhOdH64wB0"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"OSI6gp6"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" go"},"finish_reason":null}],"usage":null,"obfuscation":"fROUwYZrQ"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"o9ng7FEn6"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"GD68OsOt"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"FZHFUhgFVb"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"LxZFqnGuow"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"2vC6T7pTGu"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"bMhhwbU3fE3"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".mod"},"finish_reason":null}],"usage":null,"obfuscation":"saSnI65z"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" -"},"finish_reason":null}],"usage":null,"obfuscation":"0uLdjpaWVy"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"finish_reason":null}],"usage":null,"obfuscation":"RgYV2F2R5VT"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"Sv178By"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"4I0uMEI"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"i554cPAUE"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"qbh30LBvu"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"rwv0dv"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"l700Vh"} - data: {"id":"chatcmpl-CVGj0WCAyCdfukS4S8fIptPgzU6qc","object":"chat.completion.chunk","created":1761568494,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9872,"completion_tokens":53,"total_tokens":9925,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"HOE8"} + data: {"id":"chatcmpl-CVfOejQeCaeQHLCgJxeHpoSeMqDTx","object":"chat.completion.chunk","created":1761663332,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9875,"completion_tokens":30,"total_tokens":9905,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"cPJk"} data: [DONE] @@ -243,4 +195,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.541855125s + duration: 2.553797542s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/read_a_file.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/read_a_file.yaml index 7427314290705a36390567f831abcf4ad70871eb..b836f2997d673c751e9a3f3ac1c834be66f93db9 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/read_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/read_a_file.yaml @@ -24,21 +24,17 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"apaIEpOt1Lv30W"} + data: {"id":"chatcmpl-CVfMDiln9OYwJuTwhLVxkTnuUAInN","object":"chat.completion.chunk","created":1761663181,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WOL9laQ1Ce56Jh"} - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Understanding"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"fQI"} + data: {"id":"chatcmpl-CVfMDiln9OYwJuTwhLVxkTnuUAInN","object":"chat.completion.chunk","created":1761663181,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Reading"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Vrh4IHpun"} - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" the"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"mqEHqLJ1DgON"} + data: {"id":"chatcmpl-CVfMDiln9OYwJuTwhLVxkTnuUAInN","object":"chat.completion.chunk","created":1761663181,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Pwh05Ly8CtxiP"} - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Od2RJv56zmbd4"} + data: {"id":"chatcmpl-CVfMDiln9OYwJuTwhLVxkTnuUAInN","object":"chat.completion.chunk","created":1761663181,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Modules"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"hPUiFBe7"} - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Mod"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0uI6JRpIbhik"} + data: {"id":"chatcmpl-CVfMDiln9OYwJuTwhLVxkTnuUAInN","object":"chat.completion.chunk","created":1761663181,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"hvtqQSjs4i"} - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" File"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WqDWfUxqT7N"} - - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"x2SrMiFEUY"} - - data: {"id":"chatcmpl-CVGgMcB2H6chf7ibfnben6NUw4V9K","object":"chat.completion.chunk","created":1761568330,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":129,"completion_tokens":5,"total_tokens":134,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"jeaKOvik3s8Q6x"} + data: {"id":"chatcmpl-CVfMDiln9OYwJuTwhLVxkTnuUAInN","object":"chat.completion.chunk","created":1761663181,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":129,"completion_tokens":3,"total_tokens":132,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"HMEDXy9sgeWpNQ"} data: [DONE] @@ -47,15 +43,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.285439917s + duration: 695.326541ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44183 + content_length: 44111 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,67 +67,61 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_UHrp2FxIBmPBWK8uKz927dcg","type":"function","function":{"name":"glob","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"AqmKIu5U9S8O"} - - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"KRu5nXcdZndgbpm"} - - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pattern"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fYkCbnnjtvz"} - - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ncaex7KC1rUQw"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_4xE2NF0D4dTTbRcPHdbmr84w","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"sqXguISTvNnmqq"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"**"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"7eUOr7tM7Xbymgh"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"O"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qq5mDlC3bXJZJc"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OgahnzGO3hfcq1L"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T6ujx2Me1sdP7b"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uZbpGkldiz1V6WO"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"QsziFqEF8ErQ9"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fy50QXAuwjoS4Nv"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cCY1CvrPzilmCz"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"93BSs3GVBJlmB8D"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2eFKF3sh4MFHFYA"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PHb8y2jPpsLtsMK"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5OoaGL61zmj6NPU"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kKwfjFsZden5P"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xLulvsYSLOq9rCi"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IsNVlRQE0uS5y"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"42qJVIbEhz0EuB4"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Vz0DtgsrLtIC8"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pSI9VVAm6AGBYnE"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Xz42OBsQ3UJ1X"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TiUm1wI5nCFSm"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nmGCqm6MrT2hk"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"azPoHWoAA4SPq"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QNVCDhQMNfZtG"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TfrbrMQxN63f3"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nglZ8oV6J4uYZ"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"E"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OihKAakxSjtRK"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"O"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"D1YYaKhNoJKd6"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tqSBGyPF5nci8"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cJcoLldzhZa5e"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Hl9vizXhvKg5O"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HMtetoqF8Y1NHu7"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4JyAaCt16EtKL"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"i"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Io3wIipkD1dWGOK"} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgMerjLN2qNnrB7nzsBl0JjyKaq","object":"chat.completion.chunk","created":1761568330,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9731,"completion_tokens":301,"total_tokens":10032,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfMD1QIB4oTZrYSI8MHbVHSDyYYq","object":"chat.completion.chunk","created":1761663181,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9734,"completion_tokens":171,"total_tokens":9905,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"K"} data: [DONE] @@ -140,15 +130,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 6.721193334s + duration: 3.896481833s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44552 + content_length: 44489 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_UHrp2FxIBmPBWK8uKz927dcg\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/go.mod\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\",\"tool_call_id\":\"call_UHrp2FxIBmPBWK8uKz927dcg\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4xE2NF0D4dTTbRcPHdbmr84w\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\",\\\"depth\\\":2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_4xE2NF0D4dTTbRcPHdbmr84w\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -164,59 +154,69 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_nW2oUeDfzbnPlKYLSKSns0lV","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"FaWtILPKOThb"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_54RSa4IlGvh0PbruYbWJwMwp","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"YuCAQQAEWIgf"} + + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"fZmlHWiB3zFp2zY"} + + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1pxQSwwVv0tjIS"} + + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wdyMXOdmSVz3O"} + + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kmRKvkV5x9QTy0R"} + + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Pkc5FWVU7vpQvJD"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"XXjfsCsKk8PwlP4"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nBb2rQ45eqWmM28"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uPlnuv5upXE071"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0YznXh3Zx1ER89s"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RC2selpAqYnwG"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EpoOLxN9b3F5zM4"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lF9tAACko8YY07a"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mQ9wKWAAoGuJU"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PDOZmVk81NHoN6x"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wx7igy2xRGH6N"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DATmT5J5W99YpVG"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cnvLqaDVaE4Dz"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cjj7QjPiONh02eT"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B9RO8X79u4S6D"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SUqzbKbq9UVz2fI"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"acNl4KhnyK6zs"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aUyrUhzUek6mr"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Lx8BNjYsG24m3"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zA8qzdkUl77yi"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UUhfWD3qneO01"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wYyK6ewJSmkZM"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ymiRYNCpfX5NG"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LkLgTllmZYoXY"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xIhICIWfYjRu4D3"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wECQZy4FCy3xQO"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/read"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EJL8PrPw987cA"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"VfKnnORcUqTcn"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"limit"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ogUvP4tUatLFd"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aGPGuJzHp0uAf"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I34QmsrJ7vwEgpw"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ztC7xfYE73nLlXt"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"200"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q58vARlzg74ISxw"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EGcisw52p10JYa"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"R"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"liyXQPv48i16KWA"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"v"} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgTcKPWql6wN7Sw5eKF3Q5L3HHu","object":"chat.completion.chunk","created":1761568337,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9798,"completion_tokens":35,"total_tokens":9833,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"LkQH"} + data: {"id":"chatcmpl-CVfMH6NCVWJeIBI4UsYMQu2jBLGN1","object":"chat.completion.chunk","created":1761663185,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9811,"completion_tokens":40,"total_tokens":9851,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"Pere"} data: [DONE] @@ -225,15 +225,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.537813s + duration: 4.818397166s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44926 + content_length: 44878 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_UHrp2FxIBmPBWK8uKz927dcg\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/go.mod\\\",\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\",\"tool_call_id\":\"call_UHrp2FxIBmPBWK8uKz927dcg\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_nW2oUeDfzbnPlKYLSKSns0lV\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\n\",\"tool_call_id\":\"call_nW2oUeDfzbnPlKYLSKSns0lV\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_4xE2NF0D4dTTbRcPHdbmr84w\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file\\\",\\\"depth\\\":2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_4xE2NF0D4dTTbRcPHdbmr84w\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_54RSa4IlGvh0PbruYbWJwMwp\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/read_a_file/go.mod\\\",\\\"limit\\\":2000}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\n\",\"tool_call_id\":\"call_54RSa4IlGvh0PbruYbWJwMwp\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -249,33 +249,33 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"fqEde8fGKr"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"QkoFIHp2Wv"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"module"},"finish_reason":null}],"usage":null,"obfuscation":"HRgsG7"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"module"},"finish_reason":null}],"usage":null,"obfuscation":"umKBvx"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}],"usage":null,"obfuscation":"CpaU"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" example"},"finish_reason":null}],"usage":null,"obfuscation":"aPYY"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"ZUBfYUJv"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"nju7XOma"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/test"},"finish_reason":null}],"usage":null,"obfuscation":"AoTRdfj"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/test"},"finish_reason":null}],"usage":null,"obfuscation":"bzw0dgh"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"project"},"finish_reason":null}],"usage":null,"obfuscation":"5hsZf"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"project"},"finish_reason":null}],"usage":null,"obfuscation":"JC3z7"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"HJ5kbHidsa"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"gGN8jMzLuY"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"iYYoiLUZYk"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"sFx3yogj6V"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"5Z4hQuutbt1"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"v1mgVnjx8a6"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"HxVCGvvYGO9"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"usage":null,"obfuscation":"pjvABWN478a"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"hPd1PmlJAjc"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"XEmO3wevBJZ"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"23"},"finish_reason":null}],"usage":null,"obfuscation":"YI6WzwXAbt"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"23"},"finish_reason":null}],"usage":null,"obfuscation":"i5JJOPKh7O"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"oPJTHL"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"sapCl1"} - data: {"id":"chatcmpl-CVGgV5AEtu23NdQolISzheHyD9uF0","object":"chat.completion.chunk","created":1761568339,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9873,"completion_tokens":14,"total_tokens":9887,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"R1OQ"} + data: {"id":"chatcmpl-CVfMMJPcfio38PsvlbrefxLKoWWfu","object":"chat.completion.chunk","created":1761663190,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9891,"completion_tokens":14,"total_tokens":9905,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ocXK"} data: [DONE] @@ -284,4 +284,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.485676292s + duration: 2.339726042s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/simple_test.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/simple_test.yaml index 52f32ede82bfabd23b156143d066cb828296acf2..6addfc4b0c239f6e4437c77c7eaa926098ba0949 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/simple_test.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/simple_test.yaml @@ -24,13 +24,15 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgIlcuUPUgTFTaxIIJg2MagUj0v","object":"chat.completion.chunk","created":1761568326,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IZx6CcUfIt2KuR"} + data: {"id":"chatcmpl-CVfM8qm9phmikdosW4EUrnhhD9GDV","object":"chat.completion.chunk","created":1761663176,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Ikc5EPxVah532d"} - data: {"id":"chatcmpl-CVGgIlcuUPUgTFTaxIIJg2MagUj0v","object":"chat.completion.chunk","created":1761568326,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Greetings"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rKiBgyR"} + data: {"id":"chatcmpl-CVfM8qm9phmikdosW4EUrnhhD9GDV","object":"chat.completion.chunk","created":1761663176,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Greeting"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"d9HjQK6a"} - data: {"id":"chatcmpl-CVGgIlcuUPUgTFTaxIIJg2MagUj0v","object":"chat.completion.chunk","created":1761568326,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"DG0zqpmzVN"} + data: {"id":"chatcmpl-CVfM8qm9phmikdosW4EUrnhhD9GDV","object":"chat.completion.chunk","created":1761663176,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Inquiry"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9XM31cf0"} - data: {"id":"chatcmpl-CVGgIlcuUPUgTFTaxIIJg2MagUj0v","object":"chat.completion.chunk","created":1761568326,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":126,"completion_tokens":1,"total_tokens":127,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"EoizgPBmF7w7Nz"} + data: {"id":"chatcmpl-CVfM8qm9phmikdosW4EUrnhhD9GDV","object":"chat.completion.chunk","created":1761663176,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"vndlpXzHkm"} + + data: {"id":"chatcmpl-CVfM8qm9phmikdosW4EUrnhhD9GDV","object":"chat.completion.chunk","created":1761663176,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":126,"completion_tokens":2,"total_tokens":128,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"2SDl90JyBGlr6L"} data: [DONE] @@ -39,15 +41,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.324534041s + duration: 722.778417ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44173 + content_length: 44101 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -63,13 +65,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgJBBe4LeBM1etNfsbfRS3CaJz2","object":"chat.completion.chunk","created":1761568327,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"QFHuubDTkf"} + data: {"id":"chatcmpl-CVfM90feAsox6lcGe5oW1R3CdDH55","object":"chat.completion.chunk","created":1761663177,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"eYOwlkp1HO"} - data: {"id":"chatcmpl-CVGgJBBe4LeBM1etNfsbfRS3CaJz2","object":"chat.completion.chunk","created":1761568327,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}],"usage":null,"obfuscation":"0R4dQZuqf2"} + data: {"id":"chatcmpl-CVfM90feAsox6lcGe5oW1R3CdDH55","object":"chat.completion.chunk","created":1761663177,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hi"},"finish_reason":null}],"usage":null,"obfuscation":"k4Fee3TpAY"} - data: {"id":"chatcmpl-CVGgJBBe4LeBM1etNfsbfRS3CaJz2","object":"chat.completion.chunk","created":1761568327,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"HpmnWf"} + data: {"id":"chatcmpl-CVfM90feAsox6lcGe5oW1R3CdDH55","object":"chat.completion.chunk","created":1761663177,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"7a083Y"} - data: {"id":"chatcmpl-CVGgJBBe4LeBM1etNfsbfRS3CaJz2","object":"chat.completion.chunk","created":1761568327,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9727,"completion_tokens":10,"total_tokens":9737,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"2KWJgW1"} + data: {"id":"chatcmpl-CVfM90feAsox6lcGe5oW1R3CdDH55","object":"chat.completion.chunk","created":1761663177,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9730,"completion_tokens":74,"total_tokens":9804,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"W9j"} data: [DONE] @@ -78,4 +80,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.857978042s + duration: 3.682005167s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/sourcegraph_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/sourcegraph_tool.yaml index 597b35b520e2033d3cbda77af3055a945a4699ec..eb778515d79ec6edb398b9a660270793fee8c825 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/sourcegraph_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/sourcegraph_tool.yaml @@ -24,35 +24,35 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ixnmUJ8obB6uBi"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ePizzDvdvS6CrU"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Source"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QR7SNUWQ1Y"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Search"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"UwRRLOgUg4"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"graph"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9E1fFP2u8J9"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2gkuMdNnyXSn03"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Search"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9hUvGnwG4"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"func"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"uOCSSLoqRpiQ"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" for"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"31XxJZSjLUPv"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"khUNjcNbx1I"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" '"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Q3xUeiN9ZoH6NU"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"P8VlVgH6yWwxlcr"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"func"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"8vjQ0fzM8QC7"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"y44gM4c1Qtiyj"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pbuIr5n7cvu"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"PK8qJRLFizP9X"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"'"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"6kKbbNu09n97dVU"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Re"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"QHUbxx9TytDyN"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"n23GeR4Uz7t6a"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"positories"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"rvA3qD"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7XyPO1dq9jmkl"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Of1CcuI7w8x"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Re"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7Ij86xvDDzfZv"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" Source"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"oz35XxN1g"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"positories"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"qn0ZwJ"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"graph"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0LLvtRf8STU"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"fqiXVhGjgI"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"HRk7trwLHM"} - data: {"id":"chatcmpl-CVGiG90SMNuOn9XXeMNLflY1ElZi6","object":"chat.completion.chunk","created":1761568448,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":12,"total_tokens":150,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"bTPxPd41zU01A"} + data: {"id":"chatcmpl-CVfNv6CiDLShGMZN0Cgfl1cVqrLis","object":"chat.completion.chunk","created":1761663287,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":138,"completion_tokens":12,"total_tokens":150,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"MwkK4SmMQ0Wo1"} data: [DONE] @@ -61,15 +61,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 308.459834ms + duration: 496.019625ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44233 + content_length: 44161 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -85,79 +85,55 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_mG6jGORmOiyEtUxo6uBHVGfE","type":"function","function":{"name":"sourcegraph","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"OIbo0"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_WLV6Tr9aRugjPKQxpqRJvzIW","type":"function","function":{"name":"sourcegraph","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"NYUbO"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"y5eiRByxgjDTIWX"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"w7YzyHH9jPKG5aX"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"query"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jUaIwn1Ob8Qgt"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"query"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iZ6uYREUwHM0Z"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"7eX8MDGAhhIiP"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"8Lqekn5VEC94m"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lang"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iJc1grjUAqoZZ2"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lang"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jsKGsZ6rVFKONt"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"X"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o4zJsyQaBk"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"AUilwTsLFL63H"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":^"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bIIWDtIm6LfyY9"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8Gxs98vM2EY7vq"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TCMQH1W7wUSbS"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XaLZ0mneoqu6oG"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"ajpIcSaUPxB"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"s"}}]},"finish_reason":null}],"usage":null,"obfuscation":"x"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"GtastoCKainW5lu"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"+"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3n6tXz8C6praa"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wV94uc1VJDF0sX"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BwFf6v8xCWVXpzD"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1Xf99DoxJ5h32T"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"z"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"0KrJ037AzRM60Z"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"tMZFydBjVIs0NnF"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AaryrgE3SzpZR"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"fIkdMCNY31ribjF"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JZ251EAkQgIaugA"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sxWrqikkvYf"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MdupbA8FscIqp3D"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"P"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"GSqbZRKlsDFXzZl"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1"} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"context"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DZPkXTyR7fo"} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_window"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5gmeFB6uVTD"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mf1i1k0tr2MSqOS"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"X"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"DciJXSQFWxc5JvI"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AJmt79bFhgg"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"29LIDziuSkLnZRi"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiGqpgU8OH1rABI2q1xJfCsaESK","object":"chat.completion.chunk","created":1761568448,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9740,"completion_tokens":308,"total_tokens":10048,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfNvEKtbkXZDPh1KFVWtFlWJhkdj","object":"chat.completion.chunk","created":1761663287,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9743,"completion_tokens":424,"total_tokens":10167,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":384,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} data: [DONE] @@ -166,15 +142,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 6.971186958s + duration: 9.27407525s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 439 + content_length: 428 host: sourcegraph.com - body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go content:^func\\s+main\\("}}' + body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go \"func main\""}}' headers: Content-Type: - application/json @@ -188,144 +164,21 @@ interactions: proto_minor: 0 content_length: -1 uncompressed: true - body: '{"data":{"search":{"results":{"matchCount":0,"limitHit":false,"resultCount":0,"approximateResultCount":"0","missing":[],"timedout":[],"indexUnavailable":false,"results":[]}}}}' + body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/wx-chevalier/Go-Notes"},"file":{"path":"99~参考资料/2017~A Huge Number of Go Examples/codes/first/first/main.go","url":"/github.com/wx-chevalier/Go-Notes/-/blob/99~%E5%8F%82%E8%80%83%E8%B5%84%E6%96%99/2017~A%20Huge%20Number%20of%20Go%20Examples/codes/first/first/main.go","content":"\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// godoc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[{"preview":"// \"func main\" is special.","lineNumber":16,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":24,"offsetAndLengths":[[0,9]]},{"preview":"// func main creates a starting point for Go","lineNumber":20,"offsetAndLengths":[[3,9]]},{"preview":"\t// It only calls `func main` automatically.","lineNumber":39,"offsetAndLengths":[[19,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/wx-chevalier/Go-Notes"},"file":{"path":"99~参考资料/2017~A Huge Number of Go Examples/codes/02-write-your-first-program/main.go","url":"/github.com/wx-chevalier/Go-Notes/-/blob/99~%E5%8F%82%E8%80%83%E8%B5%84%E6%96%99/2017~A%20Huge%20Number%20of%20Go%20Examples/codes/02-write-your-first-program/main.go","content":"\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\t//\n\t// Because: Literal ~= Source Code\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[{"preview":"// \"func main\" is special.","lineNumber":16,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":24,"offsetAndLengths":[[0,9]]},{"preview":"// func main creates a starting point for Go","lineNumber":20,"offsetAndLengths":[[3,9]]},{"preview":"\t// It only calls `func main` automatically.","lineNumber":39,"offsetAndLengths":[[19,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/Go-Learning-Land/Go-Learning-Archive"},"file":{"path":"GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go","url":"/github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go","content":"// Copyright © 2021 Inanc Gumus\n// Learn Go Programming Course\n// Licencia: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// Para mas tutoriales: https://learngoprogramming.com\n// Clases particulares: https://www.linkedin.com/in/inancgumus/\n// Sigueme en twitter: https://twitter.com/inancgumus\n\n// package main es un paquete especial\n// le permite a Go crear un archivo ejecutable\npackage main\n\n/*\nEsto es un comentario multilinea.\n\nla palabra import hace que otro paquete este disponible\n para este \"archivo\" .go.\n\nimport \"fmt\" te permite acceder a la funcionaliddad del paquete fmt\n en este archivo.\n*/\nimport \"fmt\"\n\n// \"func main\" es especial.\n//\n// Go tiene que saber por donde empezar\n//\n// func main crea un punto de inicio para Go\n//\n// Despues de compilar el codigo,\n// Go ejecutara esta funcion primero.\nfunc main() {\n\t// despues del: import \"fmt\"\n\t// La funcion Println del paquete \"fmt\" estara disponible\n\n\t// Lee sobre ella escribiendo los siguiente en la consola:\n\t// go doc -src fmt Println\n\n\t// Println es simplemente una funcion exportada de:\n\t// \"fmt\" package\n\n\t// Exportada = Primera letra en mayuscula\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go no puede llamar a la funcion Println por si mismo.\n\t// Por eso la tienes que llamar aqui.\n\t// Solo llama a la `func main` de forma automatica.\n\n\t// -----\n\n\t// Go soporta caracteres unicode en cadenas de texto literal\n\t// y tambien en el codigo fuente: KÖSTEBEK!\n\t//\n\t// Porque: Literal ~= Codigo Fuente\n}\n"},"lineMatches":[{"preview":"// \"func main\" es especial.","lineNumber":23,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,9]]},{"preview":"// func main crea un punto de inicio para Go","lineNumber":27,"offsetAndLengths":[[3,9]]},{"preview":"\t// Solo llama a la `func main` de forma automatica.","lineNumber":46,"offsetAndLengths":[[21,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"translation/chinese/02-编写第一个程序/main.go","url":"/github.com/inancgumus/learngo/-/blob/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main 是一个特殊的包\n// 它允许 Go 创建一个可执行文件\npackage main\n\n/*\n这是一个多行注释\n\nimport 关键字引入另一个包\n 对于这个 .go ”文件“\n\nimport \"fmt\" 允许你使用 fmt 包的各种函数\n 在这个文件\n*/\nimport \"fmt\"\n\n// \"func main\" 是特殊的\n//\n// Go 必须知道从哪里开始执行\n//\n// func main 对于 Go 而言就是开始执行的位置\n//\n// 代码编译后，\n// Go runtime 第一个执行该函数\nfunc main() {\n\t// import \"fmt\" 之后\n\t// \"fmt\" 包中的 Println 函数就可以使用\n\n\t// 在控制台输入下面的命令可以查看它的源代码:\n\t// go doc -src fmt Println\n\n\t// Println 是一个 exported 函数来自\n\t// \"fmt\" 包\n\n\t// Exported = 首字母大写\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go 本身不能调用 Println 函数\n\t// 这就是为什么你需要在这里调用它\n\t// Go 只能自动地调用 `func main`\n\n\t// -----\n\n\t// Go 字符串支持 Unicode 字符\n\t// 源代码同时也支持: KÖSTEBEK!\n\t//\n\t// 因为: 字面值 ~= 源代码\n\n\t// 练习: 删除下行注释的 --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// 不重要的注释:\n\t// \"Merhaba Köstebek\" 的意思是 \"你好 Gopher\"\n\t// 在土耳其语\n}\n"},"lineMatches":[{"preview":"// \"func main\" 是特殊的","lineNumber":23,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,9]]},{"preview":"\t// Go 只能自动地调用 `func main`","lineNumber":46,"offsetAndLengths":[[16,9]]},{"preview":"// func main 对于 Go 而言就是开始执行的位置","lineNumber":27,"offsetAndLengths":[[3,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"first/first/main.go","url":"/github.com/inancgumus/learngo/-/blob/first/first/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[{"preview":"// \"func main\" is special.","lineNumber":23,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,9]]},{"preview":"// func main creates a starting point for Go","lineNumber":27,"offsetAndLengths":[[3,9]]},{"preview":"\t// It only calls `func main` automatically.","lineNumber":46,"offsetAndLengths":[[19,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"translation/spanish/02-tu-primer-programa/main.go","url":"/github.com/inancgumus/learngo/-/blob/translation/spanish/02-tu-primer-programa/main.go","content":"// Copyright © 2021 Inanc Gumus\n// Learn Go Programming Course\n// Licencia: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// Para mas tutoriales: https://learngoprogramming.com\n// Clases particulares: https://www.linkedin.com/in/inancgumus/\n// Sigueme en twitter: https://twitter.com/inancgumus\n\n// package main es un paquete especial\n// le permite a Go crear un archivo ejecutable\npackage main\n\n/*\nEsto es un comentario multilinea.\n\nla palabra import hace que otro paquete este disponible\n para este \"archivo\" .go.\n\nimport \"fmt\" te permite acceder a la funcionaliddad del paquete fmt\n en este archivo.\n*/\nimport \"fmt\"\n\n// \"func main\" es especial.\n//\n// Go tiene que saber por donde empezar\n//\n// func main crea un punto de inicio para Go\n//\n// Después de compilar el codigo,\n// Go ejecutará esta función primero.\nfunc main() {\n\t// después del: import \"fmt\"\n\t// La función Println del paquete \"fmt\" estará disponible\n\n\t// Lee sobre ella escribiendo los siguiente en la consola:\n\t// go doc -src fmt Println\n\n\t// Println es simplemente una función exportada de:\n\t// \"fmt\" package\n\n\t// Para poder exportar una función tendrás que escribir el\n\t// primer caracter del nombre de la función en mayúscula.\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go no puede llamar a la función Println por si mismo.\n\t// Por eso la tienes que llamar aqui.\n\t// Solo llama a la `func main` de forma automatica.\n\n\t// -----\n\n\t// Go soporta caracteres unicode en cadenas de texto literal\n\t// y tambien en el codigo fuente: KÖSTEBEK!\n\t//\n\t// Porque: Literal ~= Codigo Fuente\n}\n"},"lineMatches":[{"preview":"// \"func main\" es especial.","lineNumber":23,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,9]]},{"preview":"// func main crea un punto de inicio para Go","lineNumber":27,"offsetAndLengths":[[3,9]]},{"preview":"\t// Solo llama a la `func main` de forma automatica.","lineNumber":47,"offsetAndLengths":[[21,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/Go-Learning-Land/Go-Learning-Archive"},"file":{"path":"GolangBasics/learngo/translation/chinese/02-编写第一个程序/main.go","url":"/github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main 是一个特殊的包\n// 它允许 Go 创建一个可执行文件\npackage main\n\n/*\n这是一个多行注释\n\nimport 关键字引入另一个包\n 对于这个 .go ”文件“\n\nimport \"fmt\" 允许你使用 fmt 包的各种函数\n 在这个文件\n*/\nimport \"fmt\"\n\n// \"func main\" 是特殊的\n//\n// Go 必须知道从哪里开始执行\n//\n// func main 对于 Go 而言就是开始执行的位置\n//\n// 代码编译后，\n// Go runtime 第一个执行该函数\nfunc main() {\n\t// import \"fmt\" 之后\n\t// \"fmt\" 包中的 Println 函数就可以使用\n\n\t// 在控制台输入下面的命令可以查看它的源代码:\n\t// go doc -src fmt Println\n\n\t// Println 是一个 exported 函数来自\n\t// \"fmt\" 包\n\n\t// Exported = 首字母大写\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go 本身不能调用 Println 函数\n\t// 这就是为什么你需要在这里调用它\n\t// Go 只能自动地调用 `func main`\n\n\t// -----\n\n\t// Go 字符串支持 Unicode 字符\n\t// 源代码同时也支持: KÖSTEBEK!\n\t//\n\t// 因为: 字面值 ~= 源代码\n\n\t// 练习: 删除下行注释的 --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// 不重要的注释:\n\t// \"Merhaba Köstebek\" 的意思是 \"你好 Gopher\"\n\t// 在土耳其语\n}\n"},"lineMatches":[{"preview":"// \"func main\" 是特殊的","lineNumber":23,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,9]]},{"preview":"\t// Go 只能自动地调用 `func main`","lineNumber":46,"offsetAndLengths":[[16,9]]},{"preview":"// func main 对于 Go 而言就是开始执行的位置","lineNumber":27,"offsetAndLengths":[[3,9]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/inancgumus/learngo"},"file":{"path":"02-write-your-first-program/main.go","url":"/github.com/inancgumus/learngo/-/blob/02-write-your-first-program/main.go","content":"// Copyright © 2018 Inanc Gumus\n// Learn Go Programming Course\n// License: https://creativecommons.org/licenses/by-nc-sa/4.0/\n//\n// For more tutorials : https://learngoprogramming.com\n// In-person training : https://www.linkedin.com/in/inancgumus/\n// Follow me on twitter: https://twitter.com/inancgumus\n\n// package main is a special package\n// it allows Go to create an executable file\npackage main\n\n/*\nThis is a multi-line comment.\n\nimport keyword makes another package available\n for this .go \"file\".\n\nimport \"fmt\" lets you access fmt package''s functionality\n here in this file.\n*/\nimport \"fmt\"\n\n// \"func main\" is special.\n//\n// Go has to know where to start\n//\n// func main creates a starting point for Go\n//\n// After compiling the code,\n// Go runtime will first run this function\nfunc main() {\n\t// after: import \"fmt\"\n\t// Println function of \"fmt\" package becomes available\n\n\t// Look at what it looks like by typing in the console:\n\t// go doc -src fmt Println\n\n\t// Println is just an exported function from\n\t// \"fmt\" package\n\n\t// Exported = First Letter is uppercase\n\tfmt.Println(\"Hello Gopher!\")\n\n\t// Go cannot call Println function by itself.\n\t// That''s why you need to call it here.\n\t// It only calls `func main` automatically.\n\n\t// -----\n\n\t// Go supports Unicode characters in string literals\n\t// And also in source-code: KÖSTEBEK!\n\t//\n\t// Because: Literal ~= Source Code\n\n\t// EXERCISE: Remove the comments from below --\u003e //\n\t// fmt.Println(\"Merhaba Köstebek!\")\n\n\t// Unnecessary note:\n\t// \"Merhaba Köstebek\" means \"Hello Gopher\"\n\t// in Turkish language\n}\n"},"lineMatches":[{"preview":"// \"func main\" is special.","lineNumber":23,"offsetAndLengths":[[3,11]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,9]]}]}]}}}}' headers: Content-Type: - application/json status: 200 OK code: 200 - duration: 633.321708ms + duration: 1.339548334s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44668 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_mG6jGORmOiyEtUxo6uBHVGfE\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go content:^func\\\\\\\\s+main\\\\\\\\(\\\", \\\"count\\\": 10, \\\"context_window\\\": 5, \\\"timeout\\\": 60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 0 matches across 0 results\\n\\nNo results found. Try a different query.\\n\",\"tool_call_id\":\"call_mG6jGORmOiyEtUxo6uBHVGfE\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.openai.com/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_vEWNyKMLJn3rhTJOtUlEXgW4","type":"function","function":{"name":"sourcegraph","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"2IHjm"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"t75tgG4hxUalaAN"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"query"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Hj9B2mao8ELzK"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"KCtbw5yHYReyX"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"lang"}}]},"finish_reason":null}],"usage":null,"obfuscation":"q686K6KaQTlC6i"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CO3uaZnDRHxO2"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":":\\\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KwXz8olDwojeS"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"x"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"$"}}]},"finish_reason":null}],"usage":null,"obfuscation":"O"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"KZUt8tomPz0Jx"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f7cdzYkX6bOeK9"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K7ftsNyr3K98T"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"xHSHd1ChDyLfY"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"A10UbiwvUX6JB"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"count"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N0h8xQGBZ282n"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m06bzm08I86a9qj"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"10"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"8etGkgJ55QWugZZ"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"context"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CwqcC0r1T2y"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_window"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gNZeHanlOwv"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kSoFDps2k8Ytimo"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"RvuRTr6kQ7YVp6Y"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WWpkyc5t0Ca"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ubsUGKf1N9fNhwG"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"60"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - - data: {"id":"chatcmpl-CVGiOiryDWchQdpp2S0hb3ftOblYj","object":"chat.completion.chunk","created":1761568456,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9815,"completion_tokens":303,"total_tokens":10118,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":256,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream; charset=utf-8 - status: 200 OK - code: 200 - duration: 6.322955708s -- id: 4 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 441 - host: sourcegraph.com - body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go file:\\.go$ \"func main(\""}}' - headers: - Content-Type: - - application/json - User-Agent: - - crush/1.0 - url: https://sourcegraph.com/.api/graphql - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - uncompressed: true - body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/yunabe/lgo"},"file":{"path":"cmd/lgo-internal/liner/liner_test.go","url":"/github.com/yunabe/lgo/-/blob/cmd/lgo-internal/liner/liner_test.go","content":"package liner\n\nimport (\n\t\"testing\"\n)\n\nfunc TestContinueLine(t *testing.T) {\n\ttests := []struct {\n\t\tlines []string\n\t\texpect bool\n\t\tindent int\n\t}{{\n\t\tlines: []string{\"x +\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\" y +\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\" func\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"if\"},\n\t\texpect: true,\n\t}, {\n\t\t// syntax error.\n\t\tlines: []string{\"if {\"},\n\t\texpect: false,\n\t}, {\n\t\tlines: []string{\"for {\"},\n\t\texpect: true,\n\t\tindent: 1,\n\t}, {\n\t\tlines: []string{\"for{for{for{{\"},\n\t\texpect: true,\n\t\tindent: 4,\n\t}, {\n\t\tlines: []string{\"for{for{for{{}\"},\n\t\texpect: true,\n\t\tindent: 3,\n\t}, {\n\t\tlines: []string{\"func main()\"},\n\t\t// This is false because `func f()\u003cnewline\u003e{}` is invalid in Go`\n\t\texpect: false,\n\t}, {\n\t\t// Don''t return true even if \"missing function body\" occurrs.\n\t\tlines: []string{\"func main()\", \"func main2(){}\"},\n\t\texpect: false,\n\t}, {\n\t\tlines: []string{\"import fmt\"},\n\t\t// This must be true because `import fmt\u003cnewline\u003e\"fmt\"` is invalid.\n\t\t// TODO: Fix this\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func main(\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func main(x,\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func main(x\"},\n\t\t// Strickly speaking, this should be false if there is no possible valid statement with this.\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func (\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func (r interface{\"},\n\t\texpect: true,\n\t\tindent: 1,\n\t}, {\n\t\tlines: []string{\"/* comment \"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"`raw string\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"for {\", \"for {\"},\n\t\texpect: true,\n\t\tindent: 2,\n\t}, {\n\t\tlines: []string{\"for {\", \" \"},\n\t\texpect: true,\n\t\tindent: 1,\n\t}, {\n\t\tlines: []string{\"for {\", \"\\t\"},\n\t\texpect: true,\n\t\tindent: 1,\n\t}, {\n\t\t// This tests dropEmptyLine.\n\t\tlines: []string{\"for {\", \"\"},\n\t\texpect: true,\n\t\tindent: 1,\n\t}, {\n\t\tlines: []string{\"type s struct {}\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"type s struct {}\", \"\"},\n\t\texpect: false,\n\t}, {\n\t\tlines: []string{\"type s struct {}\", \" \"},\n\t\texpect: false,\n\t}, {\n\t\tlines: []string{\"func (s) f(){}\"},\n\t\texpect: true,\n\t}, {\n\t\tlines: []string{\"func (s) f(){}\", \"\"},\n\t\texpect: false,\n\t},\n\t}\n\n\tfor _, tc := range tests {\n\t\tt.Run(\"\", func(t *testing.T) {\n\t\t\tvar lines []string\n\t\t\tfor _, l := range tc.lines {\n\t\t\t\tlines = append(lines, l)\n\t\t\t}\n\t\t\tcont, indent := continueLine(lines)\n\t\t\tif cont != tc.expect {\n\t\t\t\tt.Errorf(\"Expected %v but got %v for %#v\", tc.expect, cont, tc.lines)\n\t\t\t\treturn\n\t\t\t}\n\t\t\tif indent != tc.indent {\n\t\t\t\tt.Errorf(\"Expected %d but got %d for %#v\", tc.indent, indent, tc.lines)\n\t\t\t}\n\t\t})\n\t}\n}\n"},"lineMatches":[{"preview":"\t\tlines: []string{\"func main(\"},","lineNumber":56,"offsetAndLengths":[[19,12]]},{"preview":"\t\tlines: []string{\"func main()\"},","lineNumber":43,"offsetAndLengths":[[19,10]]},{"preview":"\t\tlines: []string{\"func main(x\"},","lineNumber":62,"offsetAndLengths":[[19,10]]},{"preview":"\t\tlines: []string{\"func main(x,\"},","lineNumber":59,"offsetAndLengths":[[20,10]]},{"preview":"\t\tlines: []string{\"func main()\", \"func main2(){}\"},","lineNumber":48,"offsetAndLengths":[[20,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/ibarryyan/golang-tips-100"},"file":{"path":"code/code_01/main_exit.go","url":"/github.com/ibarryyan/golang-tips-100/-/blob/code/code_01/main_exit.go","content":"package main\n\nfunc main() {\n\tdefer func() {for {}}()\n\t// TODO\n}\n\nfunc main() {\n\tdefer func() { select {} }()\n\t// TODO\n}\n\nfunc main() {\n\t// TODO\n\tselect {}\n}"},"lineMatches":[{"preview":"func main() {","lineNumber":2,"offsetAndLengths":[[0,10]]},{"preview":"func main() {","lineNumber":7,"offsetAndLengths":[[0,10]]},{"preview":"func main() {","lineNumber":12,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/unigornel/unigornel"},"file":{"path":"integration_tests/tests/console/simple/main.go","url":"/github.com/unigornel/unigornel/-/blob/integration_tests/tests/console/simple/main.go","content":"package main\n\nimport \"C\"\nimport \"fmt\"\n\nfunc main() {}\n\n//export Main\nfunc Main(unused int) {\n\tfmt.Printf(\"Hello World!\\n\")\n}\n"},"lineMatches":[{"preview":"func main() {}","lineNumber":5,"offsetAndLengths":[[0,10]]},{"preview":"func Main(unused int) {","lineNumber":8,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/naeemaei/Golang-Tutorial"},"file":{"path":"15-Concurrency/09-Channels/main.go","url":"/github.com/naeemaei/Golang-Tutorial/-/blob/15-Concurrency/09-Channels/main.go","content":"package main\n\nimport \"concurrency/examples\"\n\nfunc main() {\n\texamples.RunHttpExample2()\n\t//examples.RunHttpUExample2()\n}\npackage main\n\nfunc main() {\n\t\t\n}"},"lineMatches":[{"preview":"func main() {","lineNumber":4,"offsetAndLengths":[[0,10]]},{"preview":"func main() {","lineNumber":10,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/unigornel/unigornel"},"file":{"path":"integration_tests/tests/console/sleep_and_time/main.go","url":"/github.com/unigornel/unigornel/-/blob/integration_tests/tests/console/sleep_and_time/main.go","content":"package main\n\nimport \"C\"\nimport (\n\t\"fmt\"\n\t\"time\"\n)\n\nfunc main() {}\n\n//export Main\nfunc Main(unused int) {\n\tfor {\n\t\tt := time.Now()\n\t\tfmt.Printf(\"%v [%v] Hello World!\\n\", t.UnixNano(), t.UTC())\n\t\ttime.Sleep(100 * time.Millisecond)\n\t}\n}\n"},"lineMatches":[{"preview":"func main() {}","lineNumber":8,"offsetAndLengths":[[0,10]]},{"preview":"func Main(unused int) {","lineNumber":11,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/unigornel/unigornel"},"file":{"path":"integration_tests/tests/console/read_from_console/main.go","url":"/github.com/unigornel/unigornel/-/blob/integration_tests/tests/console/read_from_console/main.go","content":"package main\n\nimport \"C\"\nimport (\n\t\"bufio\"\n\t\"fmt\"\n\t\"os\"\n\t\"strings\"\n)\n\nfunc main() {\n\tMain(0)\n}\n\n//export Main\nfunc Main(unused int) {\n\treader := bufio.NewReader(os.Stdin)\n\n\tfmt.Print(\"Hello, what''s your name? \")\n\tname, _ := reader.ReadString(''\\n'')\n\tfmt.Printf(\"Hello, %s\\n\", strings.TrimSpace(name))\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":10,"offsetAndLengths":[[0,10]]},{"preview":"func Main(unused int) {","lineNumber":15,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/MichaelCade/90DaysOfDevOps"},"file":{"path":"2022/es/Days/Go/hello.go","url":"/github.com/MichaelCade/90DaysOfDevOps/-/blob/2022/es/Days/Go/hello.go","content":"\u003c\u003c\u003c\u003c\u003c\u003c\u003c HEAD:2022/es/Days/Go/hello.go\npackage main\n\nimport \"fmt\"\n\nfunc main() {\n\tfmt.Println(\"Until tomorrow #90DaysOfDevOps\")\n}\n=======\npackage main\r\n\r\nimport \"fmt\"\r\n\r\nfunc main() {\r\n\tfmt.Println(\"Hasta mañana #90DaysOfDevOps\")\r\n}\r\n\u003e\u003e\u003e\u003e\u003e\u003e\u003e feature/translateES-03-adaptation:es/Days/Go/hello.go\n"},"lineMatches":[{"preview":"func main() {","lineNumber":5,"offsetAndLengths":[[0,10]]},{"preview":"func main() {\r","lineNumber":13,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/MichaelCade/90DaysOfDevOps"},"file":{"path":"2022/tr/Days/Go/hello.go","url":"/github.com/MichaelCade/90DaysOfDevOps/-/blob/2022/tr/Days/Go/hello.go","content":"\u003c\u003c\u003c\u003c\u003c\u003c\u003c HEAD:2022/es/Days/Go/hello.go\npackage main\n\nimport \"fmt\"\n\nfunc main() {\n\tfmt.Println(\"Until tomorrow #90DaysOfDevOps\")\n}\n=======\npackage main\r\n\r\nimport \"fmt\"\r\n\r\nfunc main() {\r\n\tfmt.Println(\"Hasta mañana #90DaysOfDevOps\")\r\n}\r\n\u003e\u003e\u003e\u003e\u003e\u003e\u003e feature/translateES-03-adaptation:es/Days/Go/hello.go\n"},"lineMatches":[{"preview":"func main() {","lineNumber":5,"offsetAndLengths":[[0,10]]},{"preview":"func main() {\r","lineNumber":13,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/gostaticanalysis/skeleton"},"file":{"path":"v2/skeleton/_template/ssa/cmd/@@.Pkg@@/main.go","url":"/github.com/gostaticanalysis/skeleton/-/blob/v2/skeleton/_template/ssa/cmd/@@.Pkg@@/main.go","content":"@@ if .Cmd -@@\npackage main\n\nimport (\n\t\"@@.Path@@\"\n\t\"golang.org/x/tools/go/analysis/@@.Checker@@checker\"\n)\n\nfunc main() { @@.Checker@@checker.Main(@@.Pkg@@.Analyzer) }\n@@ end -@@\n@@ if eq .Kind \"codegen\" -@@\npackage main\n\nimport (\n\t\"@@.Path@@\"\n\t\"github.com/gostaticanalysis/codegen/@@.Checker@@generator\"\n)\n\nfunc main() {\n\t@@.Checker@@generator.Main(@@.Pkg@@.Generator)\n}\n@@end@@\n"},"lineMatches":[{"preview":"func main() {","lineNumber":18,"offsetAndLengths":[[0,10]]},{"preview":"func main() { @@.Checker@@checker.Main(@@.Pkg@@.Analyzer) }","lineNumber":8,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/gqlgo/gqlanalysis"},"file":{"path":"cmd/gqlskeleton/_template/cmd/@@.Pkg@@/main.go","url":"/github.com/gqlgo/gqlanalysis/-/blob/cmd/gqlskeleton/_template/cmd/@@.Pkg@@/main.go","content":"@@ if .Cmd -@@\n@@ if eq .Kind \"query\" -@@\npackage main\n\nimport (\n\t\"@@.Path@@\"\n\t\"github.com/gqlgo/gqlanalysis/multichecker\"\n)\n\nfunc main() { multichecker.Main(@@.Pkg@@.Analyzer) }\n@@ end -@@\n@@ if eq .Kind \"codegen\" -@@\npackage main\n\nimport (\n\t\"@@.Path@@\"\n\t\"github.com/gqlgo/gqlanalysis/codegen\"\n)\n\nfunc main() {\n\tcodegen.Main(@@.Pkg@@.Generator)\n}\n@@ end -@@\n@@end@@\n"},"lineMatches":[{"preview":"func main() {","lineNumber":19,"offsetAndLengths":[[0,10]]},{"preview":"func main() { multichecker.Main(@@.Pkg@@.Analyzer) }","lineNumber":9,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/mateors/master_academy"},"file":{"path":"main.go","url":"/github.com/mateors/master_academy/-/blob/main.go","content":"package main\n\nimport \"fmt\"\n\n\u003c\u003c\u003c\u003c\u003c\u003c\u003c HEAD\nfunc main(){\n\n//primitive data types\n//rune, byte = alias\n//int, float32,string, bool\n\n//Composite Data Types Maps\n//Maps\n//Key = value\n\n//null\n//nil\n\n//var x map[string]string\nx := make(map[string]string)\n\nx[\"name\"] = \"Mostain\"\nx[\"height\"] = \"5.7\"\nx[\"address\"] = \"Dhaka\"\n\n//delete(x, \"height\")\n\nfmt.Println(x)\n\n}\n=======\nfunc main() {\n\n\tfmt.Println(\"Hello Bangladesh\")\n\tfmt.Println(\"github local to remote\")\n\n}\n\u003e\u003e\u003e\u003e\u003e\u003e\u003e 7a52c93944fafce3cf182700c40abfb57ed7a14b\n"},"lineMatches":[{"preview":"func main(){","lineNumber":5,"offsetAndLengths":[[0,10]]},{"preview":"func main() {","lineNumber":31,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/gostaticanalysis/skeleton"},"file":{"path":"_template/cmd/@@.Pkg@@/main.go","url":"/github.com/gostaticanalysis/skeleton/-/blob/_template/cmd/@@.Pkg@@/main.go","content":"@@ if .Cmd -@@\n@@ if (or (eq .Type \"inspect\") (eq .Type \"ssa\")) -@@\npackage main\n\nimport (\n\t\"@@.ImportPath@@\"\n\t\"golang.org/x/tools/go/analysis/@@.Checker@@checker\"\n)\n\nfunc main() { @@.Checker@@checker.Main(@@.Pkg@@.Analyzer) }\n@@ end -@@\n@@ if eq .Type \"codegen\" -@@\npackage main\n\nimport (\n\t\"@@.ImportPath@@\"\n\t\"github.com/gostaticanalysis/codegen/@@.Checker@@generator\"\n)\n\nfunc main() {\n\t@@.Checker@@generator.Main(@@.Pkg@@.Generator)\n}\n@@ end -@@\n@@end@@\n"},"lineMatches":[{"preview":"func main() {","lineNumber":19,"offsetAndLengths":[[0,10]]},{"preview":"func main() { @@.Checker@@checker.Main(@@.Pkg@@.Analyzer) }","lineNumber":9,"offsetAndLengths":[[0,10]]}]},{"__typename":"FileMatch","repository":{"name":"github.com/Avtostopom-po-Go/Avtostopom_po_Go_course"},"file":{"path":"easy level/slice.go","url":"/github.com/Avtostopom-po-Go/Avtostopom_po_Go_course/-/blob/easy%20level/slice.go","content":"package main\n\nimport \"fmt\"\n\n// 1\n// Какой будет результат выполнения приложения?\nfunc main() {\n\ta := []string{\"a\", \"b\", \"c\"}\n\tb := a[1:2]\n\tb[0] = \"q\"\n\tfmt.Println(a)\n}\n\n// 2\n// Что выведет код и почему?\nfunc mod(a []int) {\n\ta = append(a, 125)\n\tfor i := range a {\n\t\ta[i] = 5\n\t}\n\tfmt.Println(a)\n}\nfunc main() {\n\tsl := []int{1, 2, 3, 4, 5}\n\tmod(sl)\n\tfmt.Println(sl)\n}\n\n// 3\n// Что выведет код и почему?\nfunc mod(a []int) {\n\tfor i := range a {\n\t\ta[i] = 5\n\t}\n\tfmt.Println(a)\n}\nfunc main() {\n\tsl := make([]int, 4, 8)\n\tsl[0] = 1\n\tsl[1] = 2\n\tsl[2] = 3\n\tsl[3] = 5\n\tmod(sl)\n\tfmt.Println(sl)\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":6,"offsetAndLengths":[[0,10]]},{"preview":"func main() {","lineNumber":22,"offsetAndLengths":[[0,10]]}]}]}}}}' - headers: - Content-Type: - - application/json - status: 200 OK - code: 200 - duration: 1.304117041s -- id: 5 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 53172 + content_length: 65340 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_mG6jGORmOiyEtUxo6uBHVGfE\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go content:^func\\\\\\\\s+main\\\\\\\\(\\\", \\\"count\\\": 10, \\\"context_window\\\": 5, \\\"timeout\\\": 60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 0 matches across 0 results\\n\\nNo results found. Try a different query.\\n\",\"tool_call_id\":\"call_mG6jGORmOiyEtUxo6uBHVGfE\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_vEWNyKMLJn3rhTJOtUlEXgW4\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go file:\\\\\\\\.go$ \\\\\\\"func main(\\\\\\\"\\\",\\\"count\\\":10,\\\"context_window\\\":5,\\\"timeout\\\":60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/yunabe/lgo/cmd/lgo-internal/liner/liner_test.go\\n\\nURL: /github.com/yunabe/lgo/-/blob/cmd/lgo-internal/liner/liner_test.go\\n\\n```\\n51| \\t}, {\\n52| \\t\\tlines: []string{\\\"import fmt\\\"},\\n53| \\t\\t// This must be true because `import fmt\\\"fmt\\\"` is invalid.\\n54| \\t\\t// TODO: Fix this\\n55| \\t\\texpect: true,\\n56| \\t\\tlines: []string{\\\"func main(\\\"},\\n57| \\t\\tlines: []string{\\\"func main(\\\"},\\n58| \\t\\texpect: true,\\n59| \\t}, {\\n60| \\t\\tlines: []string{\\\"func main(x,\\\"},\\n61| \\t\\texpect: true,\\n```\\n\\n```\\n38| \\t\\tindent: 4,\\n39| \\t}, {\\n40| \\t\\tlines: []string{\\\"for{for{for{{}\\\"},\\n41| \\t\\texpect: true,\\n42| \\t\\tindent: 3,\\n43| \\t\\tlines: []string{\\\"func main()\\\"},\\n44| \\t\\tlines: []string{\\\"func main()\\\"},\\n45| \\t\\t// This is false because `func f(){}` is invalid in Go`\\n46| \\t\\texpect: false,\\n47| \\t}, {\\n48| \\t\\t// Don't return true even if \\\"missing function body\\\" occurrs.\\n```\\n\\n```\\n57| \\t\\tlines: []string{\\\"func main(\\\"},\\n58| \\t\\texpect: true,\\n59| \\t}, {\\n60| \\t\\tlines: []string{\\\"func main(x,\\\"},\\n61| \\t\\texpect: true,\\n62| \\t\\tlines: []string{\\\"func main(x\\\"},\\n63| \\t\\tlines: []string{\\\"func main(x\\\"},\\n64| \\t\\t// Strickly speaking, this should be false if there is no possible valid statement with this.\\n65| \\t\\texpect: true,\\n66| \\t}, {\\n67| \\t\\tlines: []string{\\\"func (\\\"},\\n```\\n\\n```\\n54| \\t\\t// TODO: Fix this\\n55| \\t\\texpect: true,\\n56| \\t}, {\\n57| \\t\\tlines: []string{\\\"func main(\\\"},\\n58| \\t\\texpect: true,\\n59| \\t\\tlines: []string{\\\"func main(x,\\\"},\\n60| \\t\\tlines: []string{\\\"func main(x,\\\"},\\n61| \\t\\texpect: true,\\n62| \\t}, {\\n63| \\t\\tlines: []string{\\\"func main(x\\\"},\\n64| \\t\\t// Strickly speaking, this should be false if there is no possible valid statement with this.\\n```\\n\\n```\\n43| \\t}, {\\n44| \\t\\tlines: []string{\\\"func main()\\\"},\\n45| \\t\\t// This is false because `func f(){}` is invalid in Go`\\n46| \\t\\texpect: false,\\n47| \\t}, {\\n48| \\t\\tlines: []string{\\\"func main()\\\", \\\"func main2(){}\\\"},\\n49| \\t\\tlines: []string{\\\"func main()\\\", \\\"func main2(){}\\\"},\\n50| \\t\\texpect: false,\\n51| \\t}, {\\n52| \\t\\tlines: []string{\\\"import fmt\\\"},\\n53| \\t\\t// This must be true because `import fmt\\\"fmt\\\"` is invalid.\\n```\\n\\n## Result 2: github.com/ibarryyan/golang-tips-100/code/code_01/main_exit.go\\n\\nURL: /github.com/ibarryyan/golang-tips-100/-/blob/code/code_01/main_exit.go\\n\\n```\\n1| package main\\n2| func main() {\\n3| func main() {\\n4| \\tdefer func() {for {}}()\\n5| \\t// TODO\\n6| }\\n7| \\n```\\n\\n```\\n2| \\n3| func main() {\\n4| \\tdefer func() {for {}}()\\n5| \\t// TODO\\n6| }\\n7| func main() {\\n8| func main() {\\n9| \\tdefer func() { select {} }()\\n10| \\t// TODO\\n11| }\\n12| \\n```\\n\\n```\\n7| \\n8| func main() {\\n9| \\tdefer func() { select {} }()\\n10| \\t// TODO\\n11| }\\n12| func main() {\\n13| func main() {\\n14| \\t// TODO\\n15| \\tselect {}\\n16| }\\n```\\n\\n## Result 3: github.com/unigornel/unigornel/integration_tests/tests/console/simple/main.go\\n\\nURL: /github.com/unigornel/unigornel/-/blob/integration_tests/tests/console/simple/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"C\\\"\\n4| import \\\"fmt\\\"\\n5| func main() {}\\n6| func main() {}\\n7| \\n8| //export Main\\n9| func Main(unused int) {\\n10| \\tfmt.Printf(\\\"Hello World!\\\\n\\\")\\n```\\n\\n```\\n3| import \\\"C\\\"\\n4| import \\\"fmt\\\"\\n5| \\n6| func main() {}\\n7| \\n8| func Main(unused int) {\\n9| func Main(unused int) {\\n10| \\tfmt.Printf(\\\"Hello World!\\\\n\\\")\\n11| }\\n12| \\n```\\n\\n## Result 4: github.com/naeemaei/Golang-Tutorial/15-Concurrency/09-Channels/main.go\\n\\nURL: /github.com/naeemaei/Golang-Tutorial/-/blob/15-Concurrency/09-Channels/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"concurrency/examples\\\"\\n4| func main() {\\n5| func main() {\\n6| \\texamples.RunHttpExample2()\\n7| \\t//examples.RunHttpUExample2()\\n8| }\\n9| package main\\n```\\n\\n```\\n5| func main() {\\n6| \\texamples.RunHttpExample2()\\n7| \\t//examples.RunHttpUExample2()\\n8| }\\n9| package main\\n10| func main() {\\n11| func main() {\\n12| \\t\\t\\n13| }\\n```\\n\\n## Result 5: github.com/unigornel/unigornel/integration_tests/tests/console/sleep_and_time/main.go\\n\\nURL: /github.com/unigornel/unigornel/-/blob/integration_tests/tests/console/sleep_and_time/main.go\\n\\n```\\n3| import \\\"C\\\"\\n4| import (\\n5| \\t\\\"fmt\\\"\\n6| \\t\\\"time\\\"\\n7| )\\n8| func main() {}\\n9| func main() {}\\n10| \\n11| //export Main\\n12| func Main(unused int) {\\n13| \\tfor {\\n```\\n\\n```\\n6| \\t\\\"time\\\"\\n7| )\\n8| \\n9| func main() {}\\n10| \\n11| func Main(unused int) {\\n12| func Main(unused int) {\\n13| \\tfor {\\n14| \\t\\tt := time.Now()\\n15| \\t\\tfmt.Printf(\\\"%v [%v] Hello World!\\\\n\\\", t.UnixNano(), t.UTC())\\n16| \\t\\ttime.Sleep(100 * time.Millisecond)\\n```\\n\\n## Result 6: github.com/unigornel/unigornel/integration_tests/tests/console/read_from_console/main.go\\n\\nURL: /github.com/unigornel/unigornel/-/blob/integration_tests/tests/console/read_from_console/main.go\\n\\n```\\n5| \\t\\\"bufio\\\"\\n6| \\t\\\"fmt\\\"\\n7| \\t\\\"os\\\"\\n8| \\t\\\"strings\\\"\\n9| )\\n10| func main() {\\n11| func main() {\\n12| \\tMain(0)\\n13| }\\n14| \\n15| //export Main\\n```\\n\\n```\\n10| \\n11| func main() {\\n12| \\tMain(0)\\n13| }\\n14| \\n15| func Main(unused int) {\\n16| func Main(unused int) {\\n17| \\treader := bufio.NewReader(os.Stdin)\\n18| \\n19| \\tfmt.Print(\\\"Hello, what's your name? \\\")\\n20| \\tname, _ := reader.ReadString('\\\\n')\\n```\\n\\n## Result 7: github.com/MichaelCade/90DaysOfDevOps/2022/es/Days/Go/hello.go\\n\\nURL: /github.com/MichaelCade/90DaysOfDevOps/-/blob/2022/es/Days/Go/hello.go\\n\\n```\\n1| <<<<<<< HEAD:2022/es/Days/Go/hello.go\\n2| package main\\n3| \\n4| import \\\"fmt\\\"\\n5| func main() {\\n6| func main() {\\n7| \\tfmt.Println(\\\"Until tomorrow #90DaysOfDevOps\\\")\\n8| }\\n9| =======\\n10| package main\\r\\n```\\n\\n```\\n8| }\\n9| =======\\n10| package main\\r\\n11| \\r\\n12| import \\\"fmt\\\"\\r\\n13| func main() {\\r\\n14| func main() {\\r\\n15| \\tfmt.Println(\\\"Hasta mañana #90DaysOfDevOps\\\")\\r\\n16| }\\r\\n17| >>>>>>> feature/translateES-03-adaptation:es/Days/Go/hello.go\\n18| \\n```\\n\\n## Result 8: github.com/MichaelCade/90DaysOfDevOps/2022/tr/Days/Go/hello.go\\n\\nURL: /github.com/MichaelCade/90DaysOfDevOps/-/blob/2022/tr/Days/Go/hello.go\\n\\n```\\n1| <<<<<<< HEAD:2022/es/Days/Go/hello.go\\n2| package main\\n3| \\n4| import \\\"fmt\\\"\\n5| func main() {\\n6| func main() {\\n7| \\tfmt.Println(\\\"Until tomorrow #90DaysOfDevOps\\\")\\n8| }\\n9| =======\\n10| package main\\r\\n```\\n\\n```\\n8| }\\n9| =======\\n10| package main\\r\\n11| \\r\\n12| import \\\"fmt\\\"\\r\\n13| func main() {\\r\\n14| func main() {\\r\\n15| \\tfmt.Println(\\\"Hasta mañana #90DaysOfDevOps\\\")\\r\\n16| }\\r\\n17| >>>>>>> feature/translateES-03-adaptation:es/Days/Go/hello.go\\n18| \\n```\\n\\n## Result 9: github.com/gostaticanalysis/skeleton/v2/skeleton/_template/ssa/cmd/@@.Pkg@@/main.go\\n\\nURL: /github.com/gostaticanalysis/skeleton/-/blob/v2/skeleton/_template/ssa/cmd/@@.Pkg@@/main.go\\n\\n```\\n13| \\n14| import (\\n15| \\t\\\"@@.Path@@\\\"\\n16| \\t\\\"github.com/gostaticanalysis/codegen/@@.Checker@@generator\\\"\\n17| )\\n18| func main() {\\n19| func main() {\\n20| \\t@@.Checker@@generator.Main(@@.Pkg@@.Generator)\\n21| }\\n22| @@end@@\\n23| \\n```\\n\\n```\\n3| \\n4| import (\\n5| \\t\\\"@@.Path@@\\\"\\n6| \\t\\\"golang.org/x/tools/go/analysis/@@.Checker@@checker\\\"\\n7| )\\n8| func main() { @@.Checker@@checker.Main(@@.Pkg@@.Analyzer) }\\n9| func main() { @@.Checker@@checker.Main(@@.Pkg@@.Analyzer) }\\n10| @@ end -@@\\n11| @@ if eq .Kind \\\"codegen\\\" -@@\\n12| package main\\n13| \\n```\\n\\n## Result 10: github.com/gqlgo/gqlanalysis/cmd/gqlskeleton/_template/cmd/@@.Pkg@@/main.go\\n\\nURL: /github.com/gqlgo/gqlanalysis/-/blob/cmd/gqlskeleton/_template/cmd/@@.Pkg@@/main.go\\n\\n```\\n14| \\n15| import (\\n16| \\t\\\"@@.Path@@\\\"\\n17| \\t\\\"github.com/gqlgo/gqlanalysis/codegen\\\"\\n18| )\\n19| func main() {\\n20| func main() {\\n21| \\tcodegen.Main(@@.Pkg@@.Generator)\\n22| }\\n23| @@ end -@@\\n24| @@end@@\\n```\\n\\n```\\n4| \\n5| import (\\n6| \\t\\\"@@.Path@@\\\"\\n7| \\t\\\"github.com/gqlgo/gqlanalysis/multichecker\\\"\\n8| )\\n9| func main() { multichecker.Main(@@.Pkg@@.Analyzer) }\\n10| func main() { multichecker.Main(@@.Pkg@@.Analyzer) }\\n11| @@ end -@@\\n12| @@ if eq .Kind \\\"codegen\\\" -@@\\n13| package main\\n14| \\n```\\n\\n\",\"tool_call_id\":\"call_vEWNyKMLJn3rhTJOtUlEXgW4\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_WLV6Tr9aRugjPKQxpqRJvzIW\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go \\\\\\\"func main\\\\\\\"\\\", \\\"count\\\": 10, \\\"timeout\\\": 60}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/wx-chevalier/Go-Notes/99~参考资料/2017~A Huge Number of Go Examples/codes/first/first/main.go\\n\\nURL: /github.com/wx-chevalier/Go-Notes/-/blob/99~%E5%8F%82%E8%80%83%E8%B5%84%E6%96%99/2017~A%20Huge%20Number%20of%20Go%20Examples/codes/first/first/main.go\\n\\n```\\n6| /*\\n7| This is a multi-line comment.\\n8| \\n9| import keyword makes another package available\\n10| for this .go \\\"file\\\".\\n11| \\n12| import \\\"fmt\\\" lets you access fmt package's functionality\\n13| here in this file.\\n14| */\\n15| import \\\"fmt\\\"\\n16| // \\\"func main\\\" is special.\\n17| // \\\"func main\\\" is special.\\n18| //\\n19| // Go has to know where to start\\n20| //\\n21| // func main creates a starting point for Go\\n22| //\\n23| // After compiling the code,\\n24| // Go runtime will first run this function\\n25| func main() {\\n26| \\t// after: import \\\"fmt\\\"\\n```\\n\\n```\\n14| */\\n15| import \\\"fmt\\\"\\n16| \\n17| // \\\"func main\\\" is special.\\n18| //\\n19| // Go has to know where to start\\n20| //\\n21| // func main creates a starting point for Go\\n22| //\\n23| // After compiling the code,\\n24| func main() {\\n25| func main() {\\n26| \\t// after: import \\\"fmt\\\"\\n27| \\t// Println function of \\\"fmt\\\" package becomes available\\n28| \\n29| \\t// Look at what it looks like by typing in the console:\\n30| \\t// godoc -src fmt Println\\n31| \\n32| \\t// Println is just an exported function from\\n33| \\t// \\\"fmt\\\" package\\n34| \\n```\\n\\n```\\n10| for this .go \\\"file\\\".\\n11| \\n12| import \\\"fmt\\\" lets you access fmt package's functionality\\n13| here in this file.\\n14| */\\n15| import \\\"fmt\\\"\\n16| \\n17| // \\\"func main\\\" is special.\\n18| //\\n19| // Go has to know where to start\\n20| // func main creates a starting point for Go\\n21| // func main creates a starting point for Go\\n22| //\\n23| // After compiling the code,\\n24| // Go runtime will first run this function\\n25| func main() {\\n26| \\t// after: import \\\"fmt\\\"\\n27| \\t// Println function of \\\"fmt\\\" package becomes available\\n28| \\n29| \\t// Look at what it looks like by typing in the console:\\n30| \\t// godoc -src fmt Println\\n```\\n\\n```\\n29| \\t// Look at what it looks like by typing in the console:\\n30| \\t// godoc -src fmt Println\\n31| \\n32| \\t// Println is just an exported function from\\n33| \\t// \\\"fmt\\\" package\\n34| \\n35| \\t// Exported = First Letter is uppercase\\n36| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n37| \\n38| \\t// Go cannot call Println function by itself.\\n39| \\t// It only calls `func main` automatically.\\n40| \\t// It only calls `func main` automatically.\\n41| \\n42| \\t// -----\\n43| \\n44| \\t// Go supports Unicode characters in string literals\\n45| \\t// And also in source-code: KÖSTEBEK!\\n46| \\n47| \\t// EXERCISE: Remove the comments from below --> //\\n48| \\t// fmt.Println(\\\"Merhaba Köstebek!\\\")\\n49| \\n```\\n\\n## Result 2: github.com/wx-chevalier/Go-Notes/99~参考资料/2017~A Huge Number of Go Examples/codes/02-write-your-first-program/main.go\\n\\nURL: /github.com/wx-chevalier/Go-Notes/-/blob/99~%E5%8F%82%E8%80%83%E8%B5%84%E6%96%99/2017~A%20Huge%20Number%20of%20Go%20Examples/codes/02-write-your-first-program/main.go\\n\\n```\\n6| /*\\n7| This is a multi-line comment.\\n8| \\n9| import keyword makes another package available\\n10| for this .go \\\"file\\\".\\n11| \\n12| import \\\"fmt\\\" lets you access fmt package's functionality\\n13| here in this file.\\n14| */\\n15| import \\\"fmt\\\"\\n16| // \\\"func main\\\" is special.\\n17| // \\\"func main\\\" is special.\\n18| //\\n19| // Go has to know where to start\\n20| //\\n21| // func main creates a starting point for Go\\n22| //\\n23| // After compiling the code,\\n24| // Go runtime will first run this function\\n25| func main() {\\n26| \\t// after: import \\\"fmt\\\"\\n```\\n\\n```\\n14| */\\n15| import \\\"fmt\\\"\\n16| \\n17| // \\\"func main\\\" is special.\\n18| //\\n19| // Go has to know where to start\\n20| //\\n21| // func main creates a starting point for Go\\n22| //\\n23| // After compiling the code,\\n24| func main() {\\n25| func main() {\\n26| \\t// after: import \\\"fmt\\\"\\n27| \\t// Println function of \\\"fmt\\\" package becomes available\\n28| \\n29| \\t// Look at what it looks like by typing in the console:\\n30| \\t// go doc -src fmt Println\\n31| \\n32| \\t// Println is just an exported function from\\n33| \\t// \\\"fmt\\\" package\\n34| \\n```\\n\\n```\\n10| for this .go \\\"file\\\".\\n11| \\n12| import \\\"fmt\\\" lets you access fmt package's functionality\\n13| here in this file.\\n14| */\\n15| import \\\"fmt\\\"\\n16| \\n17| // \\\"func main\\\" is special.\\n18| //\\n19| // Go has to know where to start\\n20| // func main creates a starting point for Go\\n21| // func main creates a starting point for Go\\n22| //\\n23| // After compiling the code,\\n24| // Go runtime will first run this function\\n25| func main() {\\n26| \\t// after: import \\\"fmt\\\"\\n27| \\t// Println function of \\\"fmt\\\" package becomes available\\n28| \\n29| \\t// Look at what it looks like by typing in the console:\\n30| \\t// go doc -src fmt Println\\n```\\n\\n```\\n29| \\t// Look at what it looks like by typing in the console:\\n30| \\t// go doc -src fmt Println\\n31| \\n32| \\t// Println is just an exported function from\\n33| \\t// \\\"fmt\\\" package\\n34| \\n35| \\t// Exported = First Letter is uppercase\\n36| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n37| \\n38| \\t// Go cannot call Println function by itself.\\n39| \\t// It only calls `func main` automatically.\\n40| \\t// It only calls `func main` automatically.\\n41| \\n42| \\t// -----\\n43| \\n44| \\t// Go supports Unicode characters in string literals\\n45| \\t// And also in source-code: KÖSTEBEK!\\n46| \\t//\\n47| \\t// Because: Literal ~= Source Code\\n48| \\n49| \\t// EXERCISE: Remove the comments from below --> //\\n```\\n\\n## Result 3: github.com/Go-Learning-Land/Go-Learning-Archive/GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go\\n\\nURL: /github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/spanish/02-tu-primer-programa/main.go\\n\\n```\\n13| /*\\n14| Esto es un comentario multilinea.\\n15| \\n16| la palabra import hace que otro paquete este disponible\\n17| para este \\\"archivo\\\" .go.\\n18| \\n19| import \\\"fmt\\\" te permite acceder a la funcionaliddad del paquete fmt\\n20| en este archivo.\\n21| */\\n22| import \\\"fmt\\\"\\n23| // \\\"func main\\\" es especial.\\n24| // \\\"func main\\\" es especial.\\n25| //\\n26| // Go tiene que saber por donde empezar\\n27| //\\n28| // func main crea un punto de inicio para Go\\n29| //\\n30| // Despues de compilar el codigo,\\n31| // Go ejecutara esta funcion primero.\\n32| func main() {\\n33| \\t// despues del: import \\\"fmt\\\"\\n```\\n\\n```\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" es especial.\\n25| //\\n26| // Go tiene que saber por donde empezar\\n27| //\\n28| // func main crea un punto de inicio para Go\\n29| //\\n30| // Despues de compilar el codigo,\\n31| func main() {\\n32| func main() {\\n33| \\t// despues del: import \\\"fmt\\\"\\n34| \\t// La funcion Println del paquete \\\"fmt\\\" estara disponible\\n35| \\n36| \\t// Lee sobre ella escribiendo los siguiente en la consola:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println es simplemente una funcion exportada de:\\n40| \\t// \\\"fmt\\\" package\\n41| \\n```\\n\\n```\\n17| para este \\\"archivo\\\" .go.\\n18| \\n19| import \\\"fmt\\\" te permite acceder a la funcionaliddad del paquete fmt\\n20| en este archivo.\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" es especial.\\n25| //\\n26| // Go tiene que saber por donde empezar\\n27| // func main crea un punto de inicio para Go\\n28| // func main crea un punto de inicio para Go\\n29| //\\n30| // Despues de compilar el codigo,\\n31| // Go ejecutara esta funcion primero.\\n32| func main() {\\n33| \\t// despues del: import \\\"fmt\\\"\\n34| \\t// La funcion Println del paquete \\\"fmt\\\" estara disponible\\n35| \\n36| \\t// Lee sobre ella escribiendo los siguiente en la consola:\\n37| \\t// go doc -src fmt Println\\n```\\n\\n```\\n36| \\t// Lee sobre ella escribiendo los siguiente en la consola:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println es simplemente una funcion exportada de:\\n40| \\t// \\\"fmt\\\" package\\n41| \\n42| \\t// Exportada = Primera letra en mayuscula\\n43| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n44| \\n45| \\t// Go no puede llamar a la funcion Println por si mismo.\\n46| \\t// Solo llama a la `func main` de forma automatica.\\n47| \\t// Solo llama a la `func main` de forma automatica.\\n48| \\n49| \\t// -----\\n50| \\n51| \\t// Go soporta caracteres unicode en cadenas de texto literal\\n52| \\t// y tambien en el codigo fuente: KÖSTEBEK!\\n53| \\t//\\n54| \\t// Porque: Literal ~= Codigo Fuente\\n55| }\\n56| \\n```\\n\\n## Result 4: github.com/inancgumus/learngo/translation/chinese/02-编写第一个程序/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go\\n\\n```\\n13| /*\\n14| 这是一个多行注释\\n15| \\n16| import 关键字引入另一个包\\n17| 对于这个 .go ”文件“\\n18| \\n19| import \\\"fmt\\\" 允许你使用 fmt 包的各种函数\\n20| 在这个文件\\n21| */\\n22| import \\\"fmt\\\"\\n23| // \\\"func main\\\" 是特殊的\\n24| // \\\"func main\\\" 是特殊的\\n25| //\\n26| // Go 必须知道从哪里开始执行\\n27| //\\n28| // func main 对于 Go 而言就是开始执行的位置\\n29| //\\n30| // 代码编译后，\\n31| // Go runtime 第一个执行该函数\\n32| func main() {\\n33| \\t// import \\\"fmt\\\" 之后\\n```\\n\\n```\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" 是特殊的\\n25| //\\n26| // Go 必须知道从哪里开始执行\\n27| //\\n28| // func main 对于 Go 而言就是开始执行的位置\\n29| //\\n30| // 代码编译后，\\n31| func main() {\\n32| func main() {\\n33| \\t// import \\\"fmt\\\" 之后\\n34| \\t// \\\"fmt\\\" 包中的 Println 函数就可以使用\\n35| \\n36| \\t// 在控制台输入下面的命令可以查看它的源代码:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println 是一个 exported 函数来自\\n40| \\t// \\\"fmt\\\" 包\\n41| \\n```\\n\\n```\\n36| \\t// 在控制台输入下面的命令可以查看它的源代码:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println 是一个 exported 函数来自\\n40| \\t// \\\"fmt\\\" 包\\n41| \\n42| \\t// Exported = 首字母大写\\n43| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n44| \\n45| \\t// Go 本身不能调用 Println 函数\\n46| \\t// Go 只能自动地调用 `func main`\\n47| \\t// Go 只能自动地调用 `func main`\\n48| \\n49| \\t// -----\\n50| \\n51| \\t// Go 字符串支持 Unicode 字符\\n52| \\t// 源代码同时也支持: KÖSTEBEK!\\n53| \\t//\\n54| \\t// 因为: 字面值 ~= 源代码\\n55| \\n56| \\t// 练习: 删除下行注释的 --> //\\n```\\n\\n```\\n17| 对于这个 .go ”文件“\\n18| \\n19| import \\\"fmt\\\" 允许你使用 fmt 包的各种函数\\n20| 在这个文件\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" 是特殊的\\n25| //\\n26| // Go 必须知道从哪里开始执行\\n27| // func main 对于 Go 而言就是开始执行的位置\\n28| // func main 对于 Go 而言就是开始执行的位置\\n29| //\\n30| // 代码编译后，\\n31| // Go runtime 第一个执行该函数\\n32| func main() {\\n33| \\t// import \\\"fmt\\\" 之后\\n34| \\t// \\\"fmt\\\" 包中的 Println 函数就可以使用\\n35| \\n36| \\t// 在控制台输入下面的命令可以查看它的源代码:\\n37| \\t// go doc -src fmt Println\\n```\\n\\n## Result 5: github.com/inancgumus/learngo/first/first/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/first/first/main.go\\n\\n```\\n13| /*\\n14| This is a multi-line comment.\\n15| \\n16| import keyword makes another package available\\n17| for this .go \\\"file\\\".\\n18| \\n19| import \\\"fmt\\\" lets you access fmt package's functionality\\n20| here in this file.\\n21| */\\n22| import \\\"fmt\\\"\\n23| // \\\"func main\\\" is special.\\n24| // \\\"func main\\\" is special.\\n25| //\\n26| // Go has to know where to start\\n27| //\\n28| // func main creates a starting point for Go\\n29| //\\n30| // After compiling the code,\\n31| // Go runtime will first run this function\\n32| func main() {\\n33| \\t// after: import \\\"fmt\\\"\\n```\\n\\n```\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" is special.\\n25| //\\n26| // Go has to know where to start\\n27| //\\n28| // func main creates a starting point for Go\\n29| //\\n30| // After compiling the code,\\n31| func main() {\\n32| func main() {\\n33| \\t// after: import \\\"fmt\\\"\\n34| \\t// Println function of \\\"fmt\\\" package becomes available\\n35| \\n36| \\t// Look at what it looks like by typing in the console:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println is just an exported function from\\n40| \\t// \\\"fmt\\\" package\\n41| \\n```\\n\\n```\\n17| for this .go \\\"file\\\".\\n18| \\n19| import \\\"fmt\\\" lets you access fmt package's functionality\\n20| here in this file.\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" is special.\\n25| //\\n26| // Go has to know where to start\\n27| // func main creates a starting point for Go\\n28| // func main creates a starting point for Go\\n29| //\\n30| // After compiling the code,\\n31| // Go runtime will first run this function\\n32| func main() {\\n33| \\t// after: import \\\"fmt\\\"\\n34| \\t// Println function of \\\"fmt\\\" package becomes available\\n35| \\n36| \\t// Look at what it looks like by typing in the console:\\n37| \\t// go doc -src fmt Println\\n```\\n\\n```\\n36| \\t// Look at what it looks like by typing in the console:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println is just an exported function from\\n40| \\t// \\\"fmt\\\" package\\n41| \\n42| \\t// Exported = First Letter is uppercase\\n43| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n44| \\n45| \\t// Go cannot call Println function by itself.\\n46| \\t// It only calls `func main` automatically.\\n47| \\t// It only calls `func main` automatically.\\n48| \\n49| \\t// -----\\n50| \\n51| \\t// Go supports Unicode characters in string literals\\n52| \\t// And also in source-code: KÖSTEBEK!\\n53| \\n54| \\t// EXERCISE: Remove the comments from below --> //\\n55| \\t// fmt.Println(\\\"Merhaba Köstebek!\\\")\\n56| \\n```\\n\\n## Result 6: github.com/inancgumus/learngo/translation/spanish/02-tu-primer-programa/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/translation/spanish/02-tu-primer-programa/main.go\\n\\n```\\n13| /*\\n14| Esto es un comentario multilinea.\\n15| \\n16| la palabra import hace que otro paquete este disponible\\n17| para este \\\"archivo\\\" .go.\\n18| \\n19| import \\\"fmt\\\" te permite acceder a la funcionaliddad del paquete fmt\\n20| en este archivo.\\n21| */\\n22| import \\\"fmt\\\"\\n23| // \\\"func main\\\" es especial.\\n24| // \\\"func main\\\" es especial.\\n25| //\\n26| // Go tiene que saber por donde empezar\\n27| //\\n28| // func main crea un punto de inicio para Go\\n29| //\\n30| // Después de compilar el codigo,\\n31| // Go ejecutará esta función primero.\\n32| func main() {\\n33| \\t// después del: import \\\"fmt\\\"\\n```\\n\\n```\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" es especial.\\n25| //\\n26| // Go tiene que saber por donde empezar\\n27| //\\n28| // func main crea un punto de inicio para Go\\n29| //\\n30| // Después de compilar el codigo,\\n31| func main() {\\n32| func main() {\\n33| \\t// después del: import \\\"fmt\\\"\\n34| \\t// La función Println del paquete \\\"fmt\\\" estará disponible\\n35| \\n36| \\t// Lee sobre ella escribiendo los siguiente en la consola:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println es simplemente una función exportada de:\\n40| \\t// \\\"fmt\\\" package\\n41| \\n```\\n\\n```\\n17| para este \\\"archivo\\\" .go.\\n18| \\n19| import \\\"fmt\\\" te permite acceder a la funcionaliddad del paquete fmt\\n20| en este archivo.\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" es especial.\\n25| //\\n26| // Go tiene que saber por donde empezar\\n27| // func main crea un punto de inicio para Go\\n28| // func main crea un punto de inicio para Go\\n29| //\\n30| // Después de compilar el codigo,\\n31| // Go ejecutará esta función primero.\\n32| func main() {\\n33| \\t// después del: import \\\"fmt\\\"\\n34| \\t// La función Println del paquete \\\"fmt\\\" estará disponible\\n35| \\n36| \\t// Lee sobre ella escribiendo los siguiente en la consola:\\n37| \\t// go doc -src fmt Println\\n```\\n\\n```\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println es simplemente una función exportada de:\\n40| \\t// \\\"fmt\\\" package\\n41| \\n42| \\t// Para poder exportar una función tendrás que escribir el\\n43| \\t// primer caracter del nombre de la función en mayúscula.\\n44| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n45| \\n46| \\t// Go no puede llamar a la función Println por si mismo.\\n47| \\t// Solo llama a la `func main` de forma automatica.\\n48| \\t// Solo llama a la `func main` de forma automatica.\\n49| \\n50| \\t// -----\\n51| \\n52| \\t// Go soporta caracteres unicode en cadenas de texto literal\\n53| \\t// y tambien en el codigo fuente: KÖSTEBEK!\\n54| \\t//\\n55| \\t// Porque: Literal ~= Codigo Fuente\\n56| }\\n57| \\n```\\n\\n## Result 7: github.com/Go-Learning-Land/Go-Learning-Archive/GolangBasics/learngo/translation/chinese/02-编写第一个程序/main.go\\n\\nURL: /github.com/Go-Learning-Land/Go-Learning-Archive/-/blob/GolangBasics/learngo/translation/chinese/02-%E7%BC%96%E5%86%99%E7%AC%AC%E4%B8%80%E4%B8%AA%E7%A8%8B%E5%BA%8F/main.go\\n\\n```\\n13| /*\\n14| 这是一个多行注释\\n15| \\n16| import 关键字引入另一个包\\n17| 对于这个 .go ”文件“\\n18| \\n19| import \\\"fmt\\\" 允许你使用 fmt 包的各种函数\\n20| 在这个文件\\n21| */\\n22| import \\\"fmt\\\"\\n23| // \\\"func main\\\" 是特殊的\\n24| // \\\"func main\\\" 是特殊的\\n25| //\\n26| // Go 必须知道从哪里开始执行\\n27| //\\n28| // func main 对于 Go 而言就是开始执行的位置\\n29| //\\n30| // 代码编译后，\\n31| // Go runtime 第一个执行该函数\\n32| func main() {\\n33| \\t// import \\\"fmt\\\" 之后\\n```\\n\\n```\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" 是特殊的\\n25| //\\n26| // Go 必须知道从哪里开始执行\\n27| //\\n28| // func main 对于 Go 而言就是开始执行的位置\\n29| //\\n30| // 代码编译后，\\n31| func main() {\\n32| func main() {\\n33| \\t// import \\\"fmt\\\" 之后\\n34| \\t// \\\"fmt\\\" 包中的 Println 函数就可以使用\\n35| \\n36| \\t// 在控制台输入下面的命令可以查看它的源代码:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println 是一个 exported 函数来自\\n40| \\t// \\\"fmt\\\" 包\\n41| \\n```\\n\\n```\\n36| \\t// 在控制台输入下面的命令可以查看它的源代码:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println 是一个 exported 函数来自\\n40| \\t// \\\"fmt\\\" 包\\n41| \\n42| \\t// Exported = 首字母大写\\n43| \\tfmt.Println(\\\"Hello Gopher!\\\")\\n44| \\n45| \\t// Go 本身不能调用 Println 函数\\n46| \\t// Go 只能自动地调用 `func main`\\n47| \\t// Go 只能自动地调用 `func main`\\n48| \\n49| \\t// -----\\n50| \\n51| \\t// Go 字符串支持 Unicode 字符\\n52| \\t// 源代码同时也支持: KÖSTEBEK!\\n53| \\t//\\n54| \\t// 因为: 字面值 ~= 源代码\\n55| \\n56| \\t// 练习: 删除下行注释的 --> //\\n```\\n\\n```\\n17| 对于这个 .go ”文件“\\n18| \\n19| import \\\"fmt\\\" 允许你使用 fmt 包的各种函数\\n20| 在这个文件\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" 是特殊的\\n25| //\\n26| // Go 必须知道从哪里开始执行\\n27| // func main 对于 Go 而言就是开始执行的位置\\n28| // func main 对于 Go 而言就是开始执行的位置\\n29| //\\n30| // 代码编译后，\\n31| // Go runtime 第一个执行该函数\\n32| func main() {\\n33| \\t// import \\\"fmt\\\" 之后\\n34| \\t// \\\"fmt\\\" 包中的 Println 函数就可以使用\\n35| \\n36| \\t// 在控制台输入下面的命令可以查看它的源代码:\\n37| \\t// go doc -src fmt Println\\n```\\n\\n## Result 8: github.com/inancgumus/learngo/02-write-your-first-program/main.go\\n\\nURL: /github.com/inancgumus/learngo/-/blob/02-write-your-first-program/main.go\\n\\n```\\n13| /*\\n14| This is a multi-line comment.\\n15| \\n16| import keyword makes another package available\\n17| for this .go \\\"file\\\".\\n18| \\n19| import \\\"fmt\\\" lets you access fmt package's functionality\\n20| here in this file.\\n21| */\\n22| import \\\"fmt\\\"\\n23| // \\\"func main\\\" is special.\\n24| // \\\"func main\\\" is special.\\n25| //\\n26| // Go has to know where to start\\n27| //\\n28| // func main creates a starting point for Go\\n29| //\\n30| // After compiling the code,\\n31| // Go runtime will first run this function\\n32| func main() {\\n33| \\t// after: import \\\"fmt\\\"\\n```\\n\\n```\\n21| */\\n22| import \\\"fmt\\\"\\n23| \\n24| // \\\"func main\\\" is special.\\n25| //\\n26| // Go has to know where to start\\n27| //\\n28| // func main creates a starting point for Go\\n29| //\\n30| // After compiling the code,\\n31| func main() {\\n32| func main() {\\n33| \\t// after: import \\\"fmt\\\"\\n34| \\t// Println function of \\\"fmt\\\" package becomes available\\n35| \\n36| \\t// Look at what it looks like by typing in the console:\\n37| \\t// go doc -src fmt Println\\n38| \\n39| \\t// Println is just an exported function from\\n40| \\t// \\\"fmt\\\" package\\n41| \\n```\\n\\n\",\"tool_call_id\":\"call_WLV6Tr9aRugjPKQxpqRJvzIW\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -341,283 +194,239 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"eZmnkNMVv7"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}],"usage":null,"obfuscation":"6YPKf2V"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"iYToGKh7Ftw"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"30"},"finish_reason":null}],"usage":null,"obfuscation":"OOQDbo62oV"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" matches"},"finish_reason":null}],"usage":null,"obfuscation":"Bk5r"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"KNsFJvsEM7Z"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" Query"},"finish_reason":null}],"usage":null,"obfuscation":"XJO87S"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"VJVD4waPvI3"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" lang"},"finish_reason":null}],"usage":null,"obfuscation":"nemuB1U"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"CbYH1ADdGjw"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"wO1iTU82VD"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" file"},"finish_reason":null}],"usage":null,"obfuscation":"iOEDMqU"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":\\"},"finish_reason":null}],"usage":null,"obfuscation":"iGTYsTeuX"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"finish_reason":null}],"usage":null,"obfuscation":"pDzwtTnqEJs"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"go"},"finish_reason":null}],"usage":null,"obfuscation":"dtNSJU9GNp"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"$"},"finish_reason":null}],"usage":null,"obfuscation":"JmTCs0ufvGq"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" \""},"finish_reason":null}],"usage":null,"obfuscation":"QHKQJaOS5"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"func"},"finish_reason":null}],"usage":null,"obfuscation":"9BWUVVlq"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" main"},"finish_reason":null}],"usage":null,"obfuscation":"DWcVaZN"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"(\"\n"},"finish_reason":null}],"usage":null,"obfuscation":"ikUn9bL"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Examples"},"finish_reason":null}],"usage":null,"obfuscation":"zY62"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"QrIKDPcXwUF"} - - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"ItQYV"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"xynOe1Q3AQ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"2kj2OHSX"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Found"},"finish_reason":null}],"usage":null,"obfuscation":"4pFS2t3"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"liaJjYhZTAZ"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" "},"finish_reason":null}],"usage":null,"obfuscation":"leudtyrxHOi"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ib"},"finish_reason":null}],"usage":null,"obfuscation":"Y51zJ8CAWB"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"30"},"finish_reason":null}],"usage":null,"obfuscation":"38c8xSsqAE"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"arry"},"finish_reason":null}],"usage":null,"obfuscation":"IVif6Vhp"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" matches"},"finish_reason":null}],"usage":null,"obfuscation":"Vjv7"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"yan"},"finish_reason":null}],"usage":null,"obfuscation":"k68hMKC6j"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" ("},"finish_reason":null}],"usage":null,"obfuscation":"N5WYe0gXpS"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/g"},"finish_reason":null}],"usage":null,"obfuscation":"7JApKVi7nd"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"limit"},"finish_reason":null}],"usage":null,"obfuscation":"FdnLzdn"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}],"usage":null,"obfuscation":"0G4Puns"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" reached"},"finish_reason":null}],"usage":null,"obfuscation":"exvI"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-t"},"finish_reason":null}],"usage":null,"obfuscation":"6r14xYEBJL"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":").\n"},"finish_reason":null}],"usage":null,"obfuscation":"0OrbsjTE"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ips"},"finish_reason":null}],"usage":null,"obfuscation":"lNG6N9lPt"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"github"},"finish_reason":null}],"usage":null,"obfuscation":"tB9ZRx"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"QUWWalnjGLC"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"fat78KTy"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"100"},"finish_reason":null}],"usage":null,"obfuscation":"ByrC2D13N"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/w"},"finish_reason":null}],"usage":null,"obfuscation":"jsxXcdSzQV"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/code"},"finish_reason":null}],"usage":null,"obfuscation":"Miq9DGb"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"x"},"finish_reason":null}],"usage":null,"obfuscation":"f6j3VxcD79v"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/code"},"finish_reason":null}],"usage":null,"obfuscation":"RxIQirr"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-che"},"finish_reason":null}],"usage":null,"obfuscation":"kh7LzyE6"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_"},"finish_reason":null}],"usage":null,"obfuscation":"NB0YWPtS1TW"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"val"},"finish_reason":null}],"usage":null,"obfuscation":"PfHXLhiX2"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"01"},"finish_reason":null}],"usage":null,"obfuscation":"nusToRt7I9"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ier"},"finish_reason":null}],"usage":null,"obfuscation":"2Kb3aYYdR"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"xm9fxsU"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"dPC5q04lIQf"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_exit"},"finish_reason":null}],"usage":null,"obfuscation":"lARuwQP"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Go"},"finish_reason":null}],"usage":null,"obfuscation":"bVqJwg9xCz"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"U8DtoLsnm"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"DdFpqVkuJvv"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"A70W6ZuHplk"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Notes"},"finish_reason":null}],"usage":null,"obfuscation":"xRdxdX3"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"3"},"finish_reason":null}],"usage":null,"obfuscation":"5re1dl3jnvy"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/-"},"finish_reason":null}],"usage":null,"obfuscation":"asz98PNuXu"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"lgA2BbuHG7X"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"vf5q1sQAq51"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"scCtI"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"blob"},"finish_reason":null}],"usage":null,"obfuscation":"U1jHYbUG"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"KCZWaadN"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"vyXJ6Tjgrmu"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/un"},"finish_reason":null}],"usage":null,"obfuscation":"jZPM2O4Fn"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"99"},"finish_reason":null}],"usage":null,"obfuscation":"qcdy3SEE9c"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ig"},"finish_reason":null}],"usage":null,"obfuscation":"nAQSfSvgxf"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"~"},"finish_reason":null}],"usage":null,"obfuscation":"ZvBzTcdLOee"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"orn"},"finish_reason":null}],"usage":null,"obfuscation":"7hYMBRh1q"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"参考"},"finish_reason":null}],"usage":null,"obfuscation":"drpu26slsx"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"el"},"finish_reason":null}],"usage":null,"obfuscation":"2FAtSKEA07"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"资料"},"finish_reason":null}],"usage":null,"obfuscation":"KpfOsHrUDc"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/un"},"finish_reason":null}],"usage":null,"obfuscation":"ZbRcfQ5Qz"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"bntBbW4sWhx"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ig"},"finish_reason":null}],"usage":null,"obfuscation":"eGLVaeHq28"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"201"},"finish_reason":null}],"usage":null,"obfuscation":"duKvmbKB8"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"orn"},"finish_reason":null}],"usage":null,"obfuscation":"CADKtawtL"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"7"},"finish_reason":null}],"usage":null,"obfuscation":"dAe4ZWT2LS7"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"el"},"finish_reason":null}],"usage":null,"obfuscation":"FIdx9wJfgG"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"~"},"finish_reason":null}],"usage":null,"obfuscation":"XIL7T3q3ZFu"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/in"},"finish_reason":null}],"usage":null,"obfuscation":"FsET3c9W1"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"A"},"finish_reason":null}],"usage":null,"obfuscation":"ZJPiOnS1zXZ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tegration"},"finish_reason":null}],"usage":null,"obfuscation":"CUp"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"%"},"finish_reason":null}],"usage":null,"obfuscation":"B9MAGSgXe6z"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tests"},"finish_reason":null}],"usage":null,"obfuscation":"XYFk79"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"20"},"finish_reason":null}],"usage":null,"obfuscation":"4LUY2LW9YJ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/tests"},"finish_reason":null}],"usage":null,"obfuscation":"5GWp1e"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Huge"},"finish_reason":null}],"usage":null,"obfuscation":"Uu6tnnLW"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"i0nUoTx6iwD"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"%"},"finish_reason":null}],"usage":null,"obfuscation":"TTAUjI31caq"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"console"},"finish_reason":null}],"usage":null,"obfuscation":"TheTN"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"20"},"finish_reason":null}],"usage":null,"obfuscation":"Vb87lDBuce"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/simple"},"finish_reason":null}],"usage":null,"obfuscation":"rqjxh"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Number"},"finish_reason":null}],"usage":null,"obfuscation":"eGr1mv"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"qOoverk"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"%"},"finish_reason":null}],"usage":null,"obfuscation":"CAQlW8awPVz"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"ehY47pBxS"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"20"},"finish_reason":null}],"usage":null,"obfuscation":"43GhuezTaK"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"ziQEnvwX8YP"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"of"},"finish_reason":null}],"usage":null,"obfuscation":"AXXjOi1WGX"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"6"},"finish_reason":null}],"usage":null,"obfuscation":"5zxibXP3QIN"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"%"},"finish_reason":null}],"usage":null,"obfuscation":"vkqxRlZnnLZ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"e1r0qefkhD5"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"20"},"finish_reason":null}],"usage":null,"obfuscation":"cxImH7jbgP"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"U2UKk"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Go"},"finish_reason":null}],"usage":null,"obfuscation":"Z0218SsvjZ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"ghqeSeqc"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"%"},"finish_reason":null}],"usage":null,"obfuscation":"SRNNZSUteJt"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/un"},"finish_reason":null}],"usage":null,"obfuscation":"OWVYjS35A"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"20"},"finish_reason":null}],"usage":null,"obfuscation":"4EXKMO0kFP"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ig"},"finish_reason":null}],"usage":null,"obfuscation":"Kh2iRJF6kK"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Examples"},"finish_reason":null}],"usage":null,"obfuscation":"8LOS"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"orn"},"finish_reason":null}],"usage":null,"obfuscation":"j873Z0DOK"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/c"},"finish_reason":null}],"usage":null,"obfuscation":"uEdASexoe8"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"el"},"finish_reason":null}],"usage":null,"obfuscation":"6AFSgIBsSj"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"odes"},"finish_reason":null}],"usage":null,"obfuscation":"LWnkBEfQ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/un"},"finish_reason":null}],"usage":null,"obfuscation":"UNNlEVWXO"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"6cycQx5QVzA"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ig"},"finish_reason":null}],"usage":null,"obfuscation":"UZUJS2EPFA"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"first"},"finish_reason":null}],"usage":null,"obfuscation":"2mlRu7U"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"orn"},"finish_reason":null}],"usage":null,"obfuscation":"1uzjg94CJ"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"ychMqNe4a6V"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"el"},"finish_reason":null}],"usage":null,"obfuscation":"XVgqgPx2V3"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"first"},"finish_reason":null}],"usage":null,"obfuscation":"0O2Soxl"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/in"},"finish_reason":null}],"usage":null,"obfuscation":"fzVpk8Ibj"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"mCA0cR2"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tegration"},"finish_reason":null}],"usage":null,"obfuscation":"BOM"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"e8039dRpl"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tests"},"finish_reason":null}],"usage":null,"obfuscation":"OplKfD"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"VJuHw3IFmk"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/tests"},"finish_reason":null}],"usage":null,"obfuscation":"0eYK4u"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"github"},"finish_reason":null}],"usage":null,"obfuscation":"KRFErC"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"TAOuQQ5Kbng"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"oaxJAuBd"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"console"},"finish_reason":null}],"usage":null,"obfuscation":"SKbFA"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/in"},"finish_reason":null}],"usage":null,"obfuscation":"4YtmHPPCX"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/s"},"finish_reason":null}],"usage":null,"obfuscation":"1A77dxPncR"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"anc"},"finish_reason":null}],"usage":null,"obfuscation":"6gSbOTVpB"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"leep"},"finish_reason":null}],"usage":null,"obfuscation":"4Z2CE3pu"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"gum"},"finish_reason":null}],"usage":null,"obfuscation":"y0QTY1HuZ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_and"},"finish_reason":null}],"usage":null,"obfuscation":"QXTO7nxG"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"us"},"finish_reason":null}],"usage":null,"obfuscation":"pOqleuDnhA"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_time"},"finish_reason":null}],"usage":null,"obfuscation":"147b7aB"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"nuuJkoh5Ak7"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"tp0r7B2"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"lear"},"finish_reason":null}],"usage":null,"obfuscation":"FR5K1Zxi"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"XTiXMLZW8"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ngo"},"finish_reason":null}],"usage":null,"obfuscation":"WVEVpzNkP"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"FmRkNoyQM4d"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/-"},"finish_reason":null}],"usage":null,"obfuscation":"H4K2m31hHV"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"9"},"finish_reason":null}],"usage":null,"obfuscation":"02Us6VqvO3N"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"VfYRJqHmD6L"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"bX2WVDi5ey7"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"blob"},"finish_reason":null}],"usage":null,"obfuscation":"SatgHXS7"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"mVkuW"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"NoqGdndifEV"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"BspRB960"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"02"},"finish_reason":null}],"usage":null,"obfuscation":"KuIfZF1HGL"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/un"},"finish_reason":null}],"usage":null,"obfuscation":"0zxIEA8xB"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-write"},"finish_reason":null}],"usage":null,"obfuscation":"DNTDzg"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ig"},"finish_reason":null}],"usage":null,"obfuscation":"X0nMj2fFqJ"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-your"},"finish_reason":null}],"usage":null,"obfuscation":"9kXJYQK"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"orn"},"finish_reason":null}],"usage":null,"obfuscation":"R82L1fX69"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-first"},"finish_reason":null}],"usage":null,"obfuscation":"R4kGTH"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"el"},"finish_reason":null}],"usage":null,"obfuscation":"aNHAdhDBT9"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-program"},"finish_reason":null}],"usage":null,"obfuscation":"TQz1"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/un"},"finish_reason":null}],"usage":null,"obfuscation":"jrIlZH8IS"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"95d5pzL"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ig"},"finish_reason":null}],"usage":null,"obfuscation":"S7QguIf4e8"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"ZYRYm5LhA"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"orn"},"finish_reason":null}],"usage":null,"obfuscation":"hvGypbVzB"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"finish_reason":null}],"usage":null,"obfuscation":"BPeSvTSSch"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"el"},"finish_reason":null}],"usage":null,"obfuscation":"Pu5m7sikak"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"github"},"finish_reason":null}],"usage":null,"obfuscation":"6KebPH"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/in"},"finish_reason":null}],"usage":null,"obfuscation":"6XhGoz83A"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"D7V9IA4O"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"tegration"},"finish_reason":null}],"usage":null,"obfuscation":"J5o"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"q0tHZlplewA"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_tests"},"finish_reason":null}],"usage":null,"obfuscation":"JmIziI"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Go"},"finish_reason":null}],"usage":null,"obfuscation":"LbalRfPwC1"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/tests"},"finish_reason":null}],"usage":null,"obfuscation":"ScB0oj"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-L"},"finish_reason":null}],"usage":null,"obfuscation":"Kw10ybWl8V"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"52CcleGtugW"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"earning"},"finish_reason":null}],"usage":null,"obfuscation":"B0pOI"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"console"},"finish_reason":null}],"usage":null,"obfuscation":"imXKx"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-L"},"finish_reason":null}],"usage":null,"obfuscation":"m79imykhqD"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/read"},"finish_reason":null}],"usage":null,"obfuscation":"2PKdxST"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"and"},"finish_reason":null}],"usage":null,"obfuscation":"55u9bpk0c"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_from"},"finish_reason":null}],"usage":null,"obfuscation":"LYviFiN"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"R57LS90F6aj"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_console"},"finish_reason":null}],"usage":null,"obfuscation":"JFY7"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Go"},"finish_reason":null}],"usage":null,"obfuscation":"V0R8JHUeOq"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"huLGlmH"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-L"},"finish_reason":null}],"usage":null,"obfuscation":"YAmnJ2An4L"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"apxeakHzL"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"earning"},"finish_reason":null}],"usage":null,"obfuscation":"360O6"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"vJYhO1jBzQO"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"bUJTScjxVue"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"11"},"finish_reason":null}],"usage":null,"obfuscation":"SYOXU3WUNW"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Archive"},"finish_reason":null}],"usage":null,"obfuscation":"kAnn9"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":";"},"finish_reason":null}],"usage":null,"obfuscation":"DiqzGzS7tWZ"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/-"},"finish_reason":null}],"usage":null,"obfuscation":"CfFNXlrfdJ"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":" github"},"finish_reason":null}],"usage":null,"obfuscation":"HE6Yu"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"XszTvr26Grg"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".com"},"finish_reason":null}],"usage":null,"obfuscation":"HBgF2Jg5"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"blob"},"finish_reason":null}],"usage":null,"obfuscation":"xM40mTKS"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"FJkZpgCd967"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/G"},"finish_reason":null}],"usage":null,"obfuscation":"2ttJyfSEI2"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"nae"},"finish_reason":null}],"usage":null,"obfuscation":"NrnuXT1kJ"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}],"usage":null,"obfuscation":"WJtjSae"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ema"},"finish_reason":null}],"usage":null,"obfuscation":"rQaW2XogW"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Basics"},"finish_reason":null}],"usage":null,"obfuscation":"tv8md1"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ei"},"finish_reason":null}],"usage":null,"obfuscation":"1tQqYAp1V6"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"86wYoEAvhjG"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/G"},"finish_reason":null}],"usage":null,"obfuscation":"9yqrIh1wGN"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"lear"},"finish_reason":null}],"usage":null,"obfuscation":"YAihhcg8"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"olang"},"finish_reason":null}],"usage":null,"obfuscation":"gdWP6gX"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"ngo"},"finish_reason":null}],"usage":null,"obfuscation":"FKOrj8XXH"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-T"},"finish_reason":null}],"usage":null,"obfuscation":"yewv4mybM0"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"TN6samlG4lq"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"utorial"},"finish_reason":null}],"usage":null,"obfuscation":"gMKqw"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"translation"},"finish_reason":null}],"usage":null,"obfuscation":"t"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"wCYltGx71e4"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/ch"},"finish_reason":null}],"usage":null,"obfuscation":"mTGHwy5F7"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"15"},"finish_reason":null}],"usage":null,"obfuscation":"kvSLcubYgy"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"inese"},"finish_reason":null}],"usage":null,"obfuscation":"DHZQYZH"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-Con"},"finish_reason":null}],"usage":null,"obfuscation":"hG5n6PNF"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"4ftvG7OwgEr"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"currency"},"finish_reason":null}],"usage":null,"obfuscation":"LIB9"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"02"},"finish_reason":null}],"usage":null,"obfuscation":"Qib5O7cXpy"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/"},"finish_reason":null}],"usage":null,"obfuscation":"UdPACIDTJl7"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-"},"finish_reason":null}],"usage":null,"obfuscation":"CVBW0XCWoZT"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"09"},"finish_reason":null}],"usage":null,"obfuscation":"b0IfzbmI3v"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"编"},"finish_reason":null}],"usage":null,"obfuscation":"rzkLNuUmY4k"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"-Ch"},"finish_reason":null}],"usage":null,"obfuscation":"AVg4nyGei"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"写"},"finish_reason":null}],"usage":null,"obfuscation":"osoNMO3tvsy"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"annels"},"finish_reason":null}],"usage":null,"obfuscation":"Cem7uw"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"第"},"finish_reason":null}],"usage":null,"obfuscation":"YM4Sc5mRSDc"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"H5rw4t4"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"一个"},"finish_reason":null}],"usage":null,"obfuscation":"Ar0QPjM2BG"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"B5ZuE29qo"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"程序"},"finish_reason":null}],"usage":null,"obfuscation":"hylnFmrGAF"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"finish_reason":null}],"usage":null,"obfuscation":"oF4LFESR6KB"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"/main"},"finish_reason":null}],"usage":null,"obfuscation":"JdV4zYd"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"finish_reason":null}],"usage":null,"obfuscation":"kkgLyp31xyq"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".go"},"finish_reason":null}],"usage":null,"obfuscation":"PFYzaIlKI"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"c64FKF"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"XZVvkY"} - data: {"id":"chatcmpl-CVGiW0Lu0dqnJ8hvxnsHnUlq7oqJr","object":"chat.completion.chunk","created":1761568464,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":12539,"completion_tokens":1041,"total_tokens":13580,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":896,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"RBiPptcAKeA94S"} + data: {"id":"chatcmpl-CVfO6rAmCfSkNhKGrySj4DnHJdCK0","object":"chat.completion.chunk","created":1761663298,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":16163,"completion_tokens":1019,"total_tokens":17182,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":896,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"2lc1TgjNZ92lWL"} data: [DONE] @@ -626,4 +435,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 13.690135541s + duration: 13.845728042s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/update_a_file.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/update_a_file.yaml index 325f8712269c6577516995e0d00e688de1520ffd..2dd7ae02ba3b628ce8a8dea0ef8994a18dadffb8 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/update_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/update_a_file.yaml @@ -24,31 +24,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"IY2Eq7gGIsOgUz"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"j63YGLvoDyULXC"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Update"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"D1nUboowC9"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Modify"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"K8DT17VSSx"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"SZwn7uaWLCD"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" print"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"tXmZkVBFZP"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"BbsF19s1OIgHO"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" message"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"f0VQqrrz"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sfrG6zaff8sk8"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" in"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"wsiSpiua2O2eU"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Print"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"KDBwSoALh8"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7M2nevlS68R"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" \""},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4kpM1gchpdQE5"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"9S8yEPgw6A7zp"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"d9PjJkD5DFI"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" file"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"J0QIBlhlREn"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" from"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4a4JFXfXaf1"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"yaRllmB9Pp"} - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":" Crush"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Lh6ynY8ifg"} - - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{"content":"\""},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Qz7L5qf0Yua76t"} - - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"o5KKiw6AYx"} - - data: {"id":"chatcmpl-CVGgWgdan0OFWBzYbomjj9H79jB7a","object":"chat.completion.chunk","created":1761568340,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_cbf1785567","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":10,"total_tokens":149,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"hLglFwp4kh5qG"} + data: {"id":"chatcmpl-CVfMOs0RaYbcYeRux2a0nPOEcnU8N","object":"chat.completion.chunk","created":1761663192,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":7,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"PX4Qck3VG26qVg"} data: [DONE] @@ -57,15 +51,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.06013175s + duration: 626.675125ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44239 + content_length: 44167 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -81,65 +75,65 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_0FYSosEsJXfwHw8AUvAGyp7A","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"p0taM3kcaOJ6m2"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_pqnbjrnfunsPMfQnAZLJrmfp","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"pfs6ZpI5Hn8sQk"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"LBoNOnDy7GMvZpV"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"i2zXIDmlvzFvbvi"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CdIfys1UstKhiq"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5yWwZIQ2h61q3L"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QGB8NfOEfFQi92x"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IzQVKDYJs5DsCLD"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"On67oDrHPNiy5X"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YEOewx9snani4F"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"24gkHTaIB9pYawD"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2D2PYZ6pfjxIDEf"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nqIkYIPoGXUVjKy"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CDd5pddfgV7jfBT"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vZKyqQTYgNUTQmQ"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bU6DWXmTRC1fbFX"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"F707oGp5YgoVy"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4hPUihmYxOYYQ"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SFongXcT200Na"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dZSGmbbUIvXc1"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WUZOec9IrUTlI"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qFTOg8u0Dj7gK"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2gGUXGHi0PH8o"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lmmjkMNRfKc4q"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rZsHPftEMFoJQ"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qnv4h8a8th9VG"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Q"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"h"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"G"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uQw5dEEt06D"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vl1l92Ss639"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RYLqKNrcYNHEy"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IF2nrW9557620"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"dh3jtnFaGVCNsqx"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"D5W4nnkvqb9lJB4"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"oyEPBStkSJvw8EH"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"YFqty5WspbBfzKL"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AI1X3O0MiiSH0"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"W46729HhLdVeF"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Fcu7wpsUYHBBQBI"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NxylFUqg1btMXmk"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"s"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"F"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"P"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"R"} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgWrBVL4Ogp2nd28fYu61iwUq23","object":"chat.completion.chunk","created":1761568340,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9741,"completion_tokens":173,"total_tokens":9914,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"L"} + data: {"id":"chatcmpl-CVfMP0I9C5sOUozIXjI6RCUEmPJ4S","object":"chat.completion.chunk","created":1761663193,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9744,"completion_tokens":109,"total_tokens":9853,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":64,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"QT"} data: [DONE] @@ -148,15 +142,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 3.747114125s + duration: 2.521306958s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44624 + content_length: 44552 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -172,59 +166,59 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_fzvHCCIhHRiXuomBi9lQ46fc","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"94kviituKK8K"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_UOJzgz3klg9lXgBH347jYRvM","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"SKPJdt9OHVNt"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"H2OMqd9OPVYy7P2"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"mp5S5IvcRk3GLix"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IB3UBny15XaPI7"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ARxKxyyYNnd24P"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7b7OokbKCIjYZ"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Mfamr6P07Y8om"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VokhM4PA1V01c72"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3JKBIAtiOoPPZCp"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N5rwC7xRmaFgy98"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kPc99JHfgF0yIQf"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2DUwyHQy1l40Lvd"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mggHTTAmLZ4Go5e"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AgqIVzX9ewie1n5"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Af6JeXpd1PoX3bW"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"R0Opyk43uimfsTH"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GS4h6kEpQDjhsaE"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Znbfp6QYW5WWX"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nXlciV7XtDbTs"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nfIV372DX9kEj"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SBWNTVVu5CV5i"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dJub2tO89gsXd"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CuKRwlC8AIhXc"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NF0ovzvdiI1vE"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zNmWh3VOm346B"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LD7MLLmrgwXJK"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3BDrA6xABEts5"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eH4gv5Fi01D"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tBrupDyw7qv"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LXiNIAd1Q4yrW"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"j7RWaapebstO6"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1i3Go5CLT6Cb6"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Binn6pGcECjBm"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YvxB414CsfAHWWz"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"o81LRcD1KEMJu6V"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XopwJoxcJ0zGDZ2"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"D7DFv2pfcenjQtQ"} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgdy3PBRC3e4m5ebgwHBeQwX2Tf","object":"chat.completion.chunk","created":1761568347,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9818,"completion_tokens":35,"total_tokens":9853,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"oBrY"} + data: {"id":"chatcmpl-CVfMRNazf7gHtmqcxeMwI3WTmhOnx","object":"chat.completion.chunk","created":1761663195,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9821,"completion_tokens":35,"total_tokens":9856,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"ttxj"} data: [DONE] @@ -233,15 +227,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.807095333s + duration: 1.374454834s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45072 + content_length: 45000 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_fzvHCCIhHRiXuomBi9lQ46fc\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_fzvHCCIhHRiXuomBi9lQ46fc\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_UOJzgz3klg9lXgBH347jYRvM\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_UOJzgz3klg9lXgBH347jYRvM\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -257,145 +251,185 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_cTB0pEK5a657Cs25BfhTssWw","type":"function","function":{"name":"edit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"L4xU5sOR6iWq"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_q4UClQoKojXGsPTWSdWUjmgA","type":"function","function":{"name":"edit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"eqw21yCxb7bd"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"CWpA1icisXA3qbF"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"RRYO4SoG8tNAD2"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HgzVgBINYahLo"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YirXb5yQ8KceeAq"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XHtYsCQRsqV9QBe"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BnIOWZGBuyWnRDZ"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lxZhY9jCU4BcCQs"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hopucoQNo9xKd8A"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GYGgZs8TUbYoQ"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MG8LK2mn0ClPJ"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"fWwnSPdDoSRmpKV"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eLCd8peAZrXaO"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GsUITcsAmoLsSV"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"He4kP4CzvDzUX"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9NibxMMXkxZmj"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Hrn9SLLHeWvEo"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"cZM8pIMgxdw4G1J"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mAQMzYLQmhPWTBa"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ehWeG3EKvKt6JnQ"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4GFcioyxqZ6bAx6"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"M"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N6LwFEBqB9NbmNe"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"A"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1ujN9JR6yC6bQ"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7WjaMNcuhWm"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kx6E2RAwKFuK2"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H7vGjlvUfEk4m"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zY3BLb0Zhc9IM"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xIqLtMBCrQRrf"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GJ8ZCXISv0wwO"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NXyKjpPHDXKGQ"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QTbjNOkSs7psoZG"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hz4mGaDr6dLJr"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m3JThHCk1SKvZ7U"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"F8KyYWD5JgQ"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"F"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"63NQ413jQOulf"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"h"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MimSaqUdbzq"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y9w8zzMfs5M"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SJ6MJbw8wAfg3"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Vx0ShpcapEMioa0"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jT96WkXiCcz2D"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QYbElzVn4SeKdss"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mWU5OTD2Xg77K"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"import"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GspJIyUuJ0Ua"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8Er9DjAOjKjYhTo"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"H9ti8bZw99MOp"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"dyH5aPsD3TcxR"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2kSmiU10AAXhYTz"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uH59MvqTRECUcYE"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"loCBa5nYHUqV"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FGrHMzrcwPW"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"wmNQFn3r3eisT"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gtn3bpX8K0U6ixs"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iVbucaoxWyEn7T"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"i8hRfj0P9aQN68"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ysmJrL1Ip3NjK"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9OxbDIv8FkFA5"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"78Nt5q39fuRcl2"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lS3R6hBO5RWjTE"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B0MAMCFLzwAnXKc"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"mBFSyRZu8eIoXK0"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"JHVNPNoWjxkBh9I"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kqLIFxjzsBuBkC2"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZsUdf3xzQE"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pGxljvwGAH"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Da5BgSonR3a8a"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"JaN6aGqycXIKC"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z4fpqrOkgqaJw"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"obXYmLfcywX8z"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"i"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GfXjKuRKkeoR"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"p3ma3YkuxaVq"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nXkTQmLbRT59Smq"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0o7Q9dK4Euc39ui"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GdqrDO2fyx8SBIt"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xaJpHNW3etkwdAN"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FZkhCVEvIXFgR9V"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CEmSPzq0A5HKZDb"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ddf5MogT4rtpA"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"rhwsZCTFTFysG"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CFlnkvxZ7y3g527"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ou4qeS0zUZBKmeV"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"L9oGdcjJRUU"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yQYLQ7ILfej"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"rOk2lHXuR88iy"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ia3OhHPOCTx4C"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6FUlxIkdiiWi7c"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"package"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hIXClBh6MkW"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XSmKfwmCisFtz"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9eI1boCR5ePpW"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"r7lnPVk9TA3uffh"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"AblHRSjjzANtLI"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iIUSL6oaWm7Xqdu"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"import"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3szICLXtjnuc"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CWea6j9CUNaOBwk"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"4vSxDc1aNnjki"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sY9kjWcjgP6u8Dj"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pcKsafVKeuDyXEo"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VVkQrzRncN"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vyxBy2FkvKGa"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"WlXJFWgz7j9LQ"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LgZSMdf88tOid"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BCpKUWuBjqxoT7l"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" from"}}]},"finish_reason":null}],"usage":null,"obfuscation":"93oCVJkvX9zS0"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qN3jwipbsjmti0"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"PsURHjjKd8W9"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uKa9d6BYZLUG3"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GwVn5tCVmtmGv"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3n2SnaNP7Pkb7N"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"p"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gWjTrMEoHKjhgSy"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sa1gkNhbBpQW4Ui"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vNyez6F9nApdjDX"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"seyFtYjtiAcj47X"} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"UcAH1p2A0F"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"DWFuNsAIAGEes"} - data: {"id":"chatcmpl-CVGgekEvq4gtGbQ3t5cZrMP4hHSUd","object":"chat.completion.chunk","created":1761568348,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9915,"completion_tokens":660,"total_tokens":10575,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bTLJIRZVgT20F"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" from"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nFbKi7dCM1VG8"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"64kgSdd7OiHT"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z5cSCH2qpUQcX"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pSgNRqDcgV3qZid"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pwpxm5OTbgKvyIh"} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + + data: {"id":"chatcmpl-CVfMTqWZMMy5vuJrMPLMMglgN0Ni3","object":"chat.completion.chunk","created":1761663197,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9918,"completion_tokens":98,"total_tokens":10016,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"5nk"} data: [DONE] @@ -404,15 +438,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 12.371268666s + duration: 1.49178325s - id: 4 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45645 + content_length: 45657 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_fzvHCCIhHRiXuomBi9lQ46fc\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_fzvHCCIhHRiXuomBi9lQ46fc\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_cTB0pEK5a657Cs25BfhTssWw\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\\n\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\\n}\\\\n\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_cTB0pEK5a657Cs25BfhTssWw\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_UOJzgz3klg9lXgBH347jYRvM\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_UOJzgz3klg9lXgBH347jYRvM\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_q4UClQoKojXGsPTWSdWUjmgA\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"package main\\\\n\\\\nimport \\\\\\\"fmt\\\\\\\"\\\\n\\\\nfunc main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\\n\\\",\\\"new_string\\\":\\\"package main\\\\n\\\\nimport \\\\\\\"fmt\\\\\\\"\\\\n\\\\nfunc main() {\\\\n\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\\n}\\\\n\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_q4UClQoKojXGsPTWSdWUjmgA\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -428,91 +462,85 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_DEI6V21pWEuSD934qa6xvQCl","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"QYzfq0X29Esb"} - - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"rIyx4c0erHA8yds"} - - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xziejyverCF"} - - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"RMBgq1JAFhUnt"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_ZMyX9QW5TvFoiJsah7IAecSX","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"sDHSyIceXtmq"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"F1q7wtEv4HwICza"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Plg4yhdM5rlj4P"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pv8L7SmYUZw"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"TLYAp6ZFjd5kl"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rpGBriKL549Dqh2"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DIejkrciZ17t8nJ"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K2YhClJ72TQhO2"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5QN6QUgubyA14mJ"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qi3k6g347Ht7D"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FFK7ZYqoNRUNUkh"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"R51OXtP53eNoX"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5rRWKqM7SrA3E9B"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IWdGoOdoocG0i"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qsHrqCm8QSHSYjw"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ma4SJZXHxYPzi"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZqWsEKFlbkOrt"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"af5oNwuolsLyR"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GcaVPVnxdNTqL"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"W5oZMrdiDzHo1"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WqdzLbyQilQB6"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8gMr334lsV0zs"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bN0vSNveORX"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SsNwRLvwGrYWl"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DTeDvfonb9HYu"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7rdBadeBBDq"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"NfNUR3OweOVfXZY"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"bZOXYvo6nyllD"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FCtzCnpbwezSU"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yZd4zGP"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iG2mw1QAJXJFI"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"LUOFIcqEYpCqr"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"57ZcHelytJo8Ipg"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"faK1Bw7x2nQXDDK"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"4HMFknp5a6QLm"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ck07u2pCoV8ZY3"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CGCptik"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kT9pq8ur6SqhYlE"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"U1pzsP3OHXYge"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" program"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CByGVwTOdV"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bNqVE9zm0OsqvOc"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" to"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xxkZyJik6haRPX2"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tXIZAcJ1Vzb5yL"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oNEZnc3mBPQfH"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MR0zSyxFawlVcBX"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" output"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4Manr09gfbn"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" program"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rs6sTWB1MR"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Shxk78YP2ppSw"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" to"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xnUi8iUtxIG5bzq"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"timeout"}}]},"finish_reason":null}],"usage":null,"obfuscation":"wKUE1JOhicI"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" verify"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MLbiAA7iSOY"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bsjDAJWvHrfxEfh"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z6xnEYBuNEezDR"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"120"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ATGimh1ekpCeIIP"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"IUiH6sOGd9buwZ"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"000"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d4Z2jun6oxLmTqU"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" output"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6iAfFC8yCmx"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ko3DWrQC1CWPIvK"} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGgrHwDxBNvCSftY0yFty3BIBbiE","object":"chat.completion.chunk","created":1761568361,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10034,"completion_tokens":52,"total_tokens":10086,"prompt_tokens_details":{"cached_tokens":9728,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"2D"} + data: {"id":"chatcmpl-CVfMULoitFvOeFsyGeFFzZHOGLVXD","object":"chat.completion.chunk","created":1761663198,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10057,"completion_tokens":49,"total_tokens":10106,"prompt_tokens_details":{"cached_tokens":9984,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"It"} data: [DONE] @@ -521,15 +549,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.790491s + duration: 1.206938083s - id: 5 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 46109 + content_length: 46112 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_0FYSosEsJXfwHw8AUvAGyp7A\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_fzvHCCIhHRiXuomBi9lQ46fc\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_fzvHCCIhHRiXuomBi9lQ46fc\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_cTB0pEK5a657Cs25BfhTssWw\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\\n\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\\n}\\\\n\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_cTB0pEK5a657Cs25BfhTssWw\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_DEI6V21pWEuSD934qa6xvQCl\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"description\\\":\\\"Run the Go program to test output\\\",\\\"timeout\\\":120000}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"hello from crush\\n\\n\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\",\"tool_call_id\":\"call_DEI6V21pWEuSD934qa6xvQCl\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_pqnbjrnfunsPMfQnAZLJrmfp\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_UOJzgz3klg9lXgBH347jYRvM\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_UOJzgz3klg9lXgBH347jYRvM\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_q4UClQoKojXGsPTWSdWUjmgA\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"package main\\\\n\\\\nimport \\\\\\\"fmt\\\\\\\"\\\\n\\\\nfunc main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\\n\\\",\\\"new_string\\\":\\\"package main\\\\n\\\\nimport \\\\\\\"fmt\\\\\\\"\\\\n\\\\nfunc main() {\\\\n\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\\n}\\\\n\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_q4UClQoKojXGsPTWSdWUjmgA\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_ZMyX9QW5TvFoiJsah7IAecSX\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"description\\\":\\\"Run the Go program to verify the new output\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"hello from crush\\n\\n\\n/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\",\"tool_call_id\":\"call_ZMyX9QW5TvFoiJsah7IAecSX\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -545,13 +573,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGgvUsP05NOa7oJzglklAn01pDbh","object":"chat.completion.chunk","created":1761568365,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"3kqnztPh3z"} + data: {"id":"chatcmpl-CVfMW5zZuvuTMfYZ0sY30P6pp97HE","object":"chat.completion.chunk","created":1761663200,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"htFcjICQTX"} - data: {"id":"chatcmpl-CVGgvUsP05NOa7oJzglklAn01pDbh","object":"chat.completion.chunk","created":1761568365,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"k1xI29ad"} + data: {"id":"chatcmpl-CVfMW5zZuvuTMfYZ0sY30P6pp97HE","object":"chat.completion.chunk","created":1761663200,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"j2stbJkP"} - data: {"id":"chatcmpl-CVGgvUsP05NOa7oJzglklAn01pDbh","object":"chat.completion.chunk","created":1761568365,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"MJkNO3"} + data: {"id":"chatcmpl-CVfMW5zZuvuTMfYZ0sY30P6pp97HE","object":"chat.completion.chunk","created":1761663200,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"lcvQR1"} - data: {"id":"chatcmpl-CVGgvUsP05NOa7oJzglklAn01pDbh","object":"chat.completion.chunk","created":1761568365,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10122,"completion_tokens":4,"total_tokens":10126,"prompt_tokens_details":{"cached_tokens":9984,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"SXs"} + data: {"id":"chatcmpl-CVfMW5zZuvuTMfYZ0sY30P6pp97HE","object":"chat.completion.chunk","created":1761663200,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":10142,"completion_tokens":4,"total_tokens":10146,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"9lJ"} data: [DONE] @@ -560,4 +588,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 2.061332292s + duration: 1.226526s diff --git a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/write_tool.yaml b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/write_tool.yaml index 7907d8554e0d27955a88b0bfdd3c7646b73393b2..66888afc4a609a08e15d725fe23cc0e747effb9d 100644 --- a/internal/agent/testdata/TestCoderAgent/openai-gpt-5/write_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openai-gpt-5/write_tool.yaml @@ -24,25 +24,27 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"i00526ssJzwsl3"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"4f43QAQEpCyyhA"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"suOtyuirSC"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":"Create"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"WzPkXnnYWT"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" config"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"jy5v2mzrs"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" a"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"FUNIZkXjgZUjqT"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":".json"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"7hI97Dt5J6A"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" config"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"eYwqpKVd7"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"6RHYW9MTMxp"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":".json"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"pyq2dFHIsWL"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Spec"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"ZBAFtp3HecS"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" file"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"YKuyHiU8dAz"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":"ified"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"2wvMGS6tpxu"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" with"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"OUGm8fLbPJH"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{"content":" Content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"XZD1dorH"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" specific"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"VgDab2M"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"tmeMGL1EMh"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{"content":" content"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"MCtFcaVk"} - data: {"id":"chatcmpl-CVGikAnxooSxlojhF3G0KR5j7Mvdq","object":"chat.completion.chunk","created":1761568478,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_eb3c3cb84d","choices":[],"usage":{"prompt_tokens":153,"completion_tokens":7,"total_tokens":160,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"l2u0BaSfnEV0wE"} + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"xYausAYJmP"} + + data: {"id":"chatcmpl-CVfOKiCaiMhxNnYtu0vIRZqI78RJW","object":"chat.completion.chunk","created":1761663312,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_65564d8ba5","choices":[],"usage":{"prompt_tokens":153,"completion_tokens":8,"total_tokens":161,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"FloMcS98ZyvPVc"} data: [DONE] @@ -51,15 +53,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 391.584125ms + duration: 652.074875ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44276 + content_length: 44204 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -75,97 +77,97 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_aYnMozO9dmgbVEodJCetI3af","type":"function","function":{"name":"write","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"wvCp9kipb5y"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_EeXNb1uQZumswRoqQHgAgGAi","type":"function","function":{"name":"write","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"GgwahHrTwuj"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"eOepwW0qt8ZY5c5"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"phxadoq15AWgSTn"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"woIr8UucyPfzfn"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zvWAQrTBSQDAl2"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"g1cyxGH3rJ8Ct"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"owj6kLggq3i4k"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FaBVUjcYdbnkWeT"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zWv2o1dRNH1SALc"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2r82FNa4U8CIw3H"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Bqi4p3t6FYjhLBp"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KY4Mto3wf0ptPsh"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KiMCZoGtScmQ5Qi"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LRHsIZRlWQSegZW"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"lQhxcPoPHO7ekMC"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QSfMK0MfppWcvL5"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d7pnDcH909Klhue"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"55ESmN29bJjm9"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0tYzkQPkcL1u8"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3lyTWAbdgbmJz"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EciDFyC1UcJWb"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0WA9GBqDrF0RX"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CVmVku0SPP7Wo"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"eccb3V24gIRJr"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xUouo2u7VCNVh"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"D1pPY16Vh40hL"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"S1TcvXZKWv4Zo"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"s"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"w"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/write"}}]},"finish_reason":null}],"usage":null,"obfuscation":"MxXWeBQqC2P8"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/write"}}]},"finish_reason":null}],"usage":null,"obfuscation":"zofVilYV1ywb"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VIbhu1zFQSsg9"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_tool"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LtrPvVMriAiOA"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/config"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4EAsH92kaBs"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/config"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2lfaPE9g3ZM"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".json"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ZHwZaGXNtdcez"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".json"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3WR7OkwO0wI8S"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"IJGdWLL7hsYZZ"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z98Ca1NFNm6zQ"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Qe1Qz68oaDa"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"content"}}]},"finish_reason":null}],"usage":null,"obfuscation":"kZ0ALfIGPOr"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ktmxgnSCD81uo"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hOXLo8L9wEK16"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"6P5IyTXQjbRRF"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"RX8kCm3Snazso"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"name"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SWD9r1J8CvFf2m"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"name"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WUvuMzS9miMfwJ"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"b5nSzQ6AmWM6s"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8csHp6m7wBImf"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"VGf7XjNf8Ucu3"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"fBYfWkwPA3Cin"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YlK3Kml7uzfCQZ"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dBxGEjCm2M7VZn"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"lbsDFNGzTB1H0"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"WlkXeUR9iozKn"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"6CcQGFXSkRAoI"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"IIm11ntKccvJC"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"version"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hwgYpWy41XX"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"version"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XFhnoM6Idss"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"oQJdOzo3zStvR"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"03fJrIvL4B1Ja"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"m2ft8PlMir6QF"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"XHPrUNzJ7UlUo"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"1"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"2"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"I"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"g"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"T"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"t"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"."}}]},"finish_reason":null}],"usage":null,"obfuscation":"c"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"0"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"ApDAZMmw5uWxQm"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"sic4AZ3QAS5nOo"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"V"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"c"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Oi2fXqkjBdpYOMu"} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XlPB0bNQVqJCicU"} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""} - data: {"id":"chatcmpl-CVGik66SzxqmwJC35qlMjzno15i6w","object":"chat.completion.chunk","created":1761568478,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9755,"completion_tokens":444,"total_tokens":10199,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":384,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} + data: {"id":"chatcmpl-CVfOLmTWld5fph4GDWkryWFGC9IiN","object":"chat.completion.chunk","created":1761663313,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9758,"completion_tokens":380,"total_tokens":10138,"prompt_tokens_details":{"cached_tokens":2688,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":320,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":""} data: [DONE] @@ -174,15 +176,15 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 7.151415292s + duration: 10.190149041s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44765 + content_length: 44693 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_aYnMozO9dmgbVEodJCetI3af\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\\",\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\n\",\"tool_call_id\":\"call_aYnMozO9dmgbVEodJCetI3af\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_EeXNb1uQZumswRoqQHgAgGAi\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\\",\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openai-gpt-5/write_tool/config.json\\n\",\"tool_call_id\":\"call_EeXNb1uQZumswRoqQHgAgGAi\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -198,13 +200,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"chatcmpl-CVGirgxIbHyTlhtV61cghElsbGeYm","object":"chat.completion.chunk","created":1761568485,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"3xJK7BzkXX"} + data: {"id":"chatcmpl-CVfOVarszi9WEHgzSz5mFugUiAnQ8","object":"chat.completion.chunk","created":1761663323,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"gxLFJzQdpU"} - data: {"id":"chatcmpl-CVGirgxIbHyTlhtV61cghElsbGeYm","object":"chat.completion.chunk","created":1761568485,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"0JTstzy2"} + data: {"id":"chatcmpl-CVfOVarszi9WEHgzSz5mFugUiAnQ8","object":"chat.completion.chunk","created":1761663323,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"v9rkceiE"} - data: {"id":"chatcmpl-CVGirgxIbHyTlhtV61cghElsbGeYm","object":"chat.completion.chunk","created":1761568485,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"D9mmaP"} + data: {"id":"chatcmpl-CVfOVarszi9WEHgzSz5mFugUiAnQ8","object":"chat.completion.chunk","created":1761663323,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"D7s5lg"} - data: {"id":"chatcmpl-CVGirgxIbHyTlhtV61cghElsbGeYm","object":"chat.completion.chunk","created":1761568485,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9848,"completion_tokens":4,"total_tokens":9852,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"TaY7f"} + data: {"id":"chatcmpl-CVfOVarszi9WEHgzSz5mFugUiAnQ8","object":"chat.completion.chunk","created":1761663323,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":9851,"completion_tokens":4,"total_tokens":9855,"prompt_tokens_details":{"cached_tokens":8832,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"IgZ45"} data: [DONE] @@ -213,4 +215,4 @@ interactions: - text/event-stream; charset=utf-8 status: 200 OK code: 200 - duration: 1.864923583s + duration: 1.839327834s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/bash_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/bash_tool.yaml index f5995e5c949dea7133560f64296a030084974008..ceb43fbaf5164145c60f33995dae3310c47b1a00 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/bash_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/bash_tool.yaml @@ -24,27 +24,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello bash using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":" using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761568516-RyL9kxWAV214dAvNh60l","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568516,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.00002964,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001974,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663383-K2u41HGLLjFeR4fxktth","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.00003195,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002115,"upstream_inference_completions_cost":0.0000108},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -53,15 +47,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 618.777917ms + duration: 561.587917ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44344 + content_length: 44272 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -77,65 +71,75 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"bash:0","type":"function","function":{"name":"bash","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"command"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.bash:0","index":0,"type":"function","function":{"name":"bash","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"echo"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"command"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" '"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" bash"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"echo"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"'"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" >"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" bash"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" >"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"description"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".txt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Create"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"description"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Create"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" with"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" content"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".txt"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" '"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" with"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" content"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" bash"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" '"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"'"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"hello"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" using"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" bash"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" echo"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"'"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" command"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568516-ZhNH8hYul1WcJiusmDC4","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568519,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10203,"completion_tokens":38,"total_tokens":10241,"cost":0.00572527,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00561165,"upstream_inference_completions_cost":0.00011362},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663383-Nhd2fpQ2R9lvzsLdP1lJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663383,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10925,"completion_tokens":41,"total_tokens":10966,"cost":0.0018191,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017166,"upstream_inference_completions_cost":0.0001025},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -144,15 +148,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 4.436289542s + duration: 2.730197458s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44655 + content_length: 44581 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.bash:0\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"echo \\\\\\\"hello bash\\\\\\\" > test.txt\\\", \\\"description\\\": \\\"Create test.txt with content 'hello bash'\\\"}\",\"name\":\"bash\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"functions.bash:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"bash:0\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"echo 'hello bash' > test.txt\\\", \\\"description\\\": \\\"Create test.txt file with content 'hello bash' using echo command\\\"}\",\"name\":\"bash\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"bash:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -168,31 +172,106 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:1","type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/bash"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":" Created"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663388-rFMClzH6ghhYHexL4web","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663388,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10985,"completion_tokens":32,"total_tokens":11017,"cost":0.0018326,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017526,"upstream_inference_completions_cost":0.00008},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + + data: [DONE] + + headers: + Content-Type: + - text/event-stream + status: 200 OK + code: 200 + duration: 2.429436375s +- id: 3 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 44871 + host: "" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"bash:0\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"echo 'hello bash' > test.txt\\\", \\\"description\\\": \\\"Create test.txt file with content 'hello bash' using echo command\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"bash:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"view:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/bash_tool/test.txt\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|hello bash\\n\\n\",\"tool_call_id\":\"view:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + headers: + Accept: + - application/json + Content-Type: + - application/json + User-Agent: + - OpenAI/Go 2.7.1 + url: https://openrouter.ai/api/v1/chat/completions + method: POST + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + content_length: -1 + body: |+ + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":" content"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":"Created"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":" test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":"hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":" bash"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":"'."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568521-THmB85Zs36vqeknfKR62","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568521,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10670,"completion_tokens":12,"total_tokens":10682,"cost":0.006432,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.006402,"upstream_inference_completions_cost":0.00003},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663391-59dhAfLxJMLFpwkA3Mvj","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663391,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11045,"completion_tokens":6,"total_tokens":11051,"cost":0.0018036,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017886,"upstream_inference_completions_cost":0.000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -201,4 +280,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 648.964834ms + duration: 1.649368375s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/download_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/download_tool.yaml index ab29dc6faeaf586b482b8ac26664b5f1f2ff471c..d2bede44a22bbd800323ea757e02dd13abecf880 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/download_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/download_tool.yaml @@ -24,21 +24,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":"Download"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":"Download"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":" example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":" example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt from example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt from example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":"-files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":"-files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":".online-convert.com"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":".online"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568522-ZTuYUxWHmOKgcj5t3hgX","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":154,"completion_tokens":10,"total_tokens":164,"cost":0.0000381,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000231,"upstream_inference_completions_cost":0.000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":"convert.com"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + + data: {"id":"gen-1761663393-oRK4e9XRMeWT1brxshNW","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":150,"completion_tokens":11,"total_tokens":161,"cost":0.0000357,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000225,"upstream_inference_completions_cost":0.0000132},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -47,15 +51,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 845.475334ms + duration: 588.401292ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44397 + content_length: 44325 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -71,11 +75,65 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568522-kfjj3CGveMbRNXeIreiY","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"download:0","type":"function","function":{"name":"download","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"url"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"https"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"://"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"example"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-files"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".online"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-con"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"vert"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".com"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/document"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/example"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568522-kfjj3CGveMbRNXeIreiY","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.download:0","function":{"arguments":"{\"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/example.txt\", \"url\": \"https://example-files.online-convert.com/document/txt/example.txt\"}","name":"download"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568522-kfjj3CGveMbRNXeIreiY","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568522,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11142,"completion_tokens":45,"total_tokens":11187,"cost":0.005661,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.005571,"upstream_inference_completions_cost":0.00009},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"example"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".txt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663393-oL9KLq8KLZJXOx8nQlNd","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663393,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10933,"completion_tokens":35,"total_tokens":10968,"cost":0.0018089,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017214,"upstream_inference_completions_cost":0.0000875},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -84,7 +142,7 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 759.602917ms + duration: 2.322705709s - id: 2 request: proto: HTTP/1.1 @@ -130,15 +188,15 @@ interactions: - text/plain; charset=UTF-8 status: 200 OK code: 200 - duration: 87.190209ms + duration: 83.719041ms - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44925 + content_length: 44769 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.download:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/example.txt\\\", \\\"url\\\": \\\"https://example-files.online-convert.com/document/txt/example.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"functions.download:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"download:0\",\"function\":{\"arguments\":\"{\\\"url\\\": \\\"https://example-files.online-convert.com/document/txt/example.txt\\\", \\\"file_path\\\": \\\"example.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"download:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -154,57 +212,37 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":" File"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":" downloaded"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":" /"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"tmp"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"/c"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"rush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"-test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":" Saved"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"/open"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"router"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"imi"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":"574"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":" bytes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":" as"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"/download"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":"example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":"/example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":".txt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":"`."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568524-gMVkHYyTwM5NmsffQi4m","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568524,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10314,"completion_tokens":24,"total_tokens":10338,"cost":0.0062484,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0061884,"upstream_inference_completions_cost":0.00006},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663397-o1VB5sbI1hPVSJfCTBCy","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663397,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11021,"completion_tokens":14,"total_tokens":11035,"cost":0.0018092,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017742,"upstream_inference_completions_cost":0.000035},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -213,4 +251,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 2.67595275s + duration: 2.046102958s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/fetch_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/fetch_tool.yaml deleted file mode 100644 index bd751f4fc0d79c8085c09df05f05db4c2c0be0ad..0000000000000000000000000000000000000000 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/fetch_tool.yaml +++ /dev/null @@ -1,255 +0,0 @@ ---- -version: 2 -interactions: -- id: 0 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 845 - host: "" - body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nfetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word ''John Doe''\n \n\n","role":"user"}],"model":"qwen/qwen3-next-80b-a3b-instruct","max_tokens":40,"stream_options":{"include_usage":true},"usage":{"include":true},"stream":true}' - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://openrouter.ai/api/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":"Check"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":" if"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":" example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":".html"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":" contains"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":" John"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":" Doe"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761568527-YXiJhQNClogNRxPR2kjt","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568527,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":155,"completion_tokens":8,"total_tokens":163,"cost":0.0000305,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000217,"upstream_inference_completions_cost":0.0000088},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream - status: 200 OK - code: 200 - duration: 618.6605ms -- id: 1 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 44415 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://openrouter.ai/api/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.fetch:0","index":0,"type":"function","function":{"name":"fetch","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"url"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"https"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"://"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"example"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-files"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".online"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-con"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"vert"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".com"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"website"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/html"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/example"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".html"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"format"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"text"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} - - data: {"id":"gen-1761568527-PVPYs3IsljUbOAVN8nda","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568543,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10218,"completion_tokens":34,"total_tokens":10252,"cost":0.00572156,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0056199,"upstream_inference_completions_cost":0.00010166},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream - status: 200 OK - code: 200 - duration: 10.124457958s -- id: 2 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 0 - host: example-files.online-convert.com - headers: - User-Agent: - - crush/1.0 - url: https://example-files.online-convert.com/website/html/example.html - method: GET - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - uncompressed: true - body: |- - - - - - -

HTML test file

- -

Purpose: Provide example of this file type
- Document file type: HTML
- Version: 1.0
- Remark:

- -

- - Example content:
- The names "John Doe" for males, "Jane Doe" or "Jane Roe" for females, or "Jonnie Doe" and "Janie Doe" for children, or just "Doe" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.

- -

John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series.

- -

Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases.

- -

- - File created by https://www.online-convert.com
- More example files: https://www.online-convert.com/file-type
- Text of "Example content": Wikipedia
- License: Attribution-ShareAlike 3.0 Unported - -

- -

Feel free to use and share the file according to license above.

- - - - headers: - Content-Type: - - text/html; charset=UTF-8 - status: 200 OK - code: 200 - duration: 48.824208ms -- id: 3 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 47211 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.fetch:0\",\"function\":{\"arguments\":\"{\\\"url\\\": \\\"https://example-files.online-convert.com/website/html/example.html\\\", \\\"format\\\": \\\"text\\\"}\",\"name\":\"fetch\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"HTML test file Purpose: Provide example of this file type Document file type: HTML Version: 1.0 Remark: Example content: The names \\\"John Doe\\\" for males, \\\"Jane Doe\\\" or \\\"Jane Roe\\\" for females, or \\\"Jonnie Doe\\\" and \\\"Janie Doe\\\" for children, or just \\\"Doe\\\" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of \\\"John Doe\\\" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand. John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series. Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, \\\"John Doe v. Jane Roe\\\". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) \\\"John Doe\\\"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases. File created by https://www.online-convert.com More example files: https://www.online-convert.com/file-type Text of \\\"Example content\\\": Wikipedia License: Attribution-ShareAlike 3.0 Unported Feel free to use and share the file according to license above.\",\"tool_call_id\":\"functions.fetch:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://openrouter.ai/api/v1/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":"Yes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":", the content contains the word"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":"John Doe'."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761568545-HaGSzI7QzE1xUajKTXiO","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568546,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11131,"completion_tokens":12,"total_tokens":11143,"cost":0.011167,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.011131,"upstream_inference_completions_cost":0.000036},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream - status: 200 OK - code: 200 - duration: 2.630210125s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/glob_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/glob_tool.yaml index 698aec1356ed4eaa5823268392aec9cfac699d7a..9f601e472856bb132c2a793dee00874d9bca406b 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/glob_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/glob_tool.yaml @@ -24,31 +24,31 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" all"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" all"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" ."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" ."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" using"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":" glob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":" glob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761568547-A8LqjOlxsuNXarVj6g5L","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":139,"completion_tokens":11,"total_tokens":150,"cost":0.00003156,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001946,"upstream_inference_completions_cost":0.0000121},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663413-P62iMlylSDbesyEeCNqy","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663413,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":139,"completion_tokens":11,"total_tokens":150,"cost":0.000026,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000139,"upstream_inference_completions_cost":0.0000121},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -57,15 +57,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 616.1375ms + duration: 768.62575ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44333 + content_length: 44261 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -81,23 +81,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.glob:0","index":0,"type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"glob:0","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"pattern"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"pattern"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"*."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"*."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568548-Zw7wyvC3ITYIzympz6jt","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568548,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10201,"completion_tokens":16,"total_tokens":10217,"cost":0.00565839,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00561055,"upstream_inference_completions_cost":0.00004784},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663413-wLM5cYxs4HXL1irYuTJb","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663414,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10923,"completion_tokens":15,"total_tokens":10938,"cost":0.0017529,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017154,"upstream_inference_completions_cost":0.0000375},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -106,15 +108,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.50320375s + duration: 2.653864291s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44608 + content_length: 44516 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool/main.go\",\"tool_call_id\":\"functions.glob:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/glob_tool/main.go\",\"tool_call_id\":\"glob:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -130,63 +132,15 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":" `/"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"tmp"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"/c"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"rush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"-test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"/open"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"router"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"imi"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"/g"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"lob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"/main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663416-utSy43CYdElhR9nrXkBk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663416,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663416-utSy43CYdElhR9nrXkBk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663416,"choices":[{"index":0,"delta":{"role":"assistant","content":"main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663416-utSy43CYdElhR9nrXkBk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663416,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663416-utSy43CYdElhR9nrXkBk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663416,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568549-2OFzET1WgY1FOn0axKPp","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568549,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10327,"completion_tokens":26,"total_tokens":10353,"cost":0.0041828,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0041308,"upstream_inference_completions_cost":0.000052},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663416-utSy43CYdElhR9nrXkBk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663416,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10972,"completion_tokens":3,"total_tokens":10975,"cost":0.0017523,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017448,"upstream_inference_completions_cost":0.0000075},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -195,4 +149,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 4.633432s + duration: 1.641015458s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/grep_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/grep_tool.yaml index fc9203b9e223a40c57767f089bf6cea45fc963ff..b704c023d12c700ed823e170bdaff52cd4d8d506 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/grep_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/grep_tool.yaml @@ -24,19 +24,17 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-xOeNR41Tucke1vPV49JQ","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663418,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-xOeNR41Tucke1vPV49JQ","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663418,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-xOeNR41Tucke1vPV49JQ","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663418,"choices":[{"index":0,"delta":{"role":"assistant","content":" for package in Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":" for package in Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-xOeNR41Tucke1vPV49JQ","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663418,"choices":[{"index":0,"delta":{"role":"assistant","content":" files using grep"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":" files using grep"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-xOeNR41Tucke1vPV49JQ","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663418,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761569094-JynqNDKXnjQbi1SAA7uQ","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569094,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":140,"completion_tokens":9,"total_tokens":149,"cost":0.0000295,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000196,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663418-xOeNR41Tucke1vPV49JQ","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663418,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":140,"completion_tokens":9,"total_tokens":149,"cost":0.0000447,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000042,"upstream_inference_completions_cost":0.0000027},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -45,15 +43,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 584.888125ms + duration: 1.378490084s - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44331 + content_length: 44259 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -69,35 +67,37 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"grep:0","type":"function","function":{"name":"grep","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.grep:0","index":0,"type":"function","function":{"name":"grep","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"pattern"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"pattern"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"package"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"package"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"include"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"include"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"*."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"*."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569094-1GdPBvtsEKaANTmdkduc","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569095,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10202,"completion_tokens":23,"total_tokens":10225,"cost":0.0061787,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0061212,"upstream_inference_completions_cost":0.0000575},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663418-bxggCbRtJR0SScqYQDnh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663419,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10924,"completion_tokens":22,"total_tokens":10946,"cost":0.001771,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001716,"upstream_inference_completions_cost":0.000055},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -106,15 +106,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 3.144410333s + duration: 2.208485042s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44684 + content_length: 44592 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.grep:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"package\\\", \\\"include\\\": \\\"*.go\\\"}\",\"name\":\"grep\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"functions.grep:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"grep:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"package\\\", \\\"include\\\": \\\"*.go\\\"}\",\"name\":\"grep\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"grep:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -130,29 +130,65 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":" match"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":" `/"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"tmp"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"/c"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"rush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"-test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"/open"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"router"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"imi"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"/g"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"rep"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":" match"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"/main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569097-eHXanBB95DXcSyL5J61l","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569097,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11003,"completion_tokens":10,"total_tokens":11013,"cost":0.0066268,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0066018,"upstream_inference_completions_cost":0.000025},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663421-TexPcDeofler0LFhxcAo","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663421,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10999,"completion_tokens":28,"total_tokens":11027,"cost":0.001831,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001761,"upstream_inference_completions_cost":0.00007},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -161,4 +197,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 3.019712209s + duration: 2.675038416s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/ls_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/ls_tool.yaml index 20df43317e1ee861ef922a6f8781d7c24887c81a..fe8e25c96502a923ac8f950d7413f879a6a9922f 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/ls_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/ls_tool.yaml @@ -24,19 +24,17 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663425-shUhmWj4YZ3iptJVZMNo","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663425-shUhmWj4YZ3iptJVZMNo","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":"List"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":"List"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663425-shUhmWj4YZ3iptJVZMNo","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":" files in current directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":" files in current directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663425-shUhmWj4YZ3iptJVZMNo","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":" using ls"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":" using ls"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663425-shUhmWj4YZ3iptJVZMNo","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761569101-TtIOfTGCpXrP5vbrikIM","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":137,"completion_tokens":8,"total_tokens":145,"cost":0.00002798,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001918,"upstream_inference_completions_cost":0.0000088},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663425-shUhmWj4YZ3iptJVZMNo","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":137,"completion_tokens":8,"total_tokens":145,"cost":0.00003255,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002055,"upstream_inference_completions_cost":0.000012},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -45,15 +43,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 285.355208ms + duration: 1.034993125s - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44325 + content_length: 44253 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -69,11 +67,55 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569101-pC8fT1ZASQxCMBX6qFWD","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"ls:0","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569101-pC8fT1ZASQxCMBX6qFWD","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.ls:0","function":{"arguments":"{}","name":"ls"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569101-pC8fT1ZASQxCMBX6qFWD","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569101,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11124,"completion_tokens":2,"total_tokens":11126,"cost":0.005566,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.005562,"upstream_inference_completions_cost":0.000004},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ls"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663425-vH8IR8CCnpEjwXHY2vJ4","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663425,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10921,"completion_tokens":31,"total_tokens":10952,"cost":0.0017917,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017142,"upstream_inference_completions_cost":0.0000775},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -82,15 +124,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 366.880083ms + duration: 2.97482525s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44595 + content_length: 44574 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.ls:0\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"functions.ls:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"ls:0\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool\\\"}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -106,11 +148,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569102-gwZPIiBSnJXke8xXfQuU","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569102,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":".mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569102-gwZPIiBSnJXke8xXfQuU","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569102,"choices":[{"index":0,"delta":{"role":"assistant","content":"go.mod, main.go"},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569102-gwZPIiBSnJXke8xXfQuU","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569102,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10343,"completion_tokens":5,"total_tokens":10348,"cost":0.0051815,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0051715,"upstream_inference_completions_cost":0.00001},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663428-jj9DmBi6oFr3DsfRB2k3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663428,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10998,"completion_tokens":6,"total_tokens":11004,"cost":0.0017754,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017604,"upstream_inference_completions_cost":0.000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -119,4 +171,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 250.439458ms + duration: 1.837167792s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/multiedit_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/multiedit_tool.yaml index fba80a124ac30725516e9e9a4050a67e9be64a6f..c97888659f4bbc87fa927368e231ba6bc7c25f57 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/multiedit_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/multiedit_tool.yaml @@ -24,21 +24,37 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":"Use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"Use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":" multiedit to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":" update greeting"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":" and add comment in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":" main.go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569103-Zz1p16Wps6BNZDMsX4uw","provider":"GMICloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569103,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":160,"completion_tokens":14,"total_tokens":174,"cost":0.000045,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000024,"upstream_inference_completions_cost":0.000021},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" greeting"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" add"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + + data: {"id":"gen-1761663431-9w62WSqNusEUlRFYfGU3","provider":"AtlasCloud","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":160,"completion_tokens":14,"total_tokens":174,"cost":0.000045,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000024,"upstream_inference_completions_cost":0.000021},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -47,15 +63,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.651823333s + duration: 760.225333ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44411 + content_length: 44339 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -71,13 +87,117 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569103-tJ9GKWT8V15Mo3McyHwH","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569104,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" help"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" you"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" make"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" those"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" Let"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" me"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" first"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" read"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" understand"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" its"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":" structure"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569103-tJ9GKWT8V15Mo3McyHwH","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569104,"choices":[{"index":0,"delta":{"role":"assistant","content":"I'll use multiedit to make both changes to main.go at once."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569103-tJ9GKWT8V15Mo3McyHwH","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569104,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","function":{"arguments":"{\"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\"}","name":"view"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:0","type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569103-tJ9GKWT8V15Mo3McyHwH","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569104,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11145,"completion_tokens":39,"total_tokens":11184,"cost":0.0056505,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0055725,"upstream_inference_completions_cost":0.000078},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/mult"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ied"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"it"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663431-MYZTdU3cUXiSryra5lxS","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663431,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10945,"completion_tokens":61,"total_tokens":11006,"cost":0.0018811,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017286,"upstream_inference_completions_cost":0.0001525},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -86,15 +206,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.693470042s + duration: 2.22171175s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44913 + content_length: 44887 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll use multiedit to make both changes to main.go at once.\",\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you use multiedit to make those changes in main.go. Let me first read the file to understand its current structure.\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -110,11 +230,245 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569106-jWcdxnV1SplIzv7HAlFr","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569106,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"Now"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" I'll"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" use"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" make"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" both"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" -"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" add"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" above"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" fmt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":".Println"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" change"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" string"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" World"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"!'"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" '"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"!"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":"'."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"multiedit:1","type":"function","function":{"name":"multiedit","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/mult"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ied"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"it"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ed"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"its"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" [\n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" {\n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"old"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_string"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569106-jWcdxnV1SplIzv7HAlFr","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569106,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.multiedit:1","function":{"arguments":"{\"edits\": [{\"old_string\": \"\\tfmt.Println(\\\"Hello, World!\\\")\", \"new_string\": \"\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\"}], \"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\"}","name":"multiedit"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"func"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569106-jWcdxnV1SplIzv7HAlFr","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569106,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11231,"completion_tokens":57,"total_tokens":11288,"cost":0.0057295,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0056155,"upstream_inference_completions_cost":0.000114},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"()"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" {\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\t"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"fmt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".Println"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"(\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" World"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"!\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\")"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\",\n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"new"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_string"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"func"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"()"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" {\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\t"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"//"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" G"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"reeting"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\t"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"fmt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".Println"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"(\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" Crush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"!\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\")"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"\n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" }\n"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"]}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663436-pqM8ceDA9NyOC8d6R9ca","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663436,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11074,"completion_tokens":127,"total_tokens":11201,"cost":0.0021235,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001806,"upstream_inference_completions_cost":0.0003175},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -123,15 +477,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 436.165916ms + duration: 1.869071792s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45476 + content_length: 45638 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll use multiedit to make both changes to main.go at once.\",\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"functions.multiedit:1\",\"function\":{\"arguments\":\"{\\\"edits\\\": [{\\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\", \\\"new_string\\\": \\\"\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"}], \\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"functions.multiedit:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you use multiedit to make those changes in main.go. Let me first read the file to understand its current structure.\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"},{\"content\":\"Now I'll use multiedit to make both changes - add the comment above fmt.Println and change the string from 'Hello, World!' to 'Hello, Crush!'.\",\"tool_calls\":[{\"id\":\"multiedit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\", \\\"edits\\\": [\\n {\\n \\\"old_string\\\": \\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\n \\\"new_string\\\": \\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"\\n }\\n]}\",\"name\":\"multiedit\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"multiedit:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -147,25 +501,180 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:2","type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/mult"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"ied"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"it"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663445-INa2ySPUMI0b2e6tSCLD","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663445,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11253,"completion_tokens":34,"total_tokens":11287,"cost":0.0018832,"is_byok":false,"prompt_tokens_details":{"cached_tokens":11008,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017982,"upstream_inference_completions_cost":0.000085},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + + data: [DONE] + + headers: + Content-Type: + - text/event-stream + status: 200 OK + code: 200 + duration: 2.667102375s +- id: 4 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 46070 + host: "" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"I'll help you use multiedit to make those changes in main.go. Let me first read the file to understand its current structure.\",\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"},{\"content\":\"Now I'll use multiedit to make both changes - add the comment above fmt.Println and change the string from 'Hello, World!' to 'Hello, Crush!'.\",\"tool_calls\":[{\"id\":\"multiedit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\", \\\"edits\\\": [\\n {\\n \\\"old_string\\\": \\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\n \\\"new_string\\\": \\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\"\\n }\\n]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"multiedit:1\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"view:2\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\t// Greeting\\n 7|\\tfmt.Println(\\\"Hello, Crush!\\\")\\n 8|}\\n\\n\",\"tool_call_id\":\"view:2\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + headers: + Accept: + - application/json + Content-Type: + - application/json + User-Agent: + - OpenAI/Go 2.7.1 + url: https://openrouter.ai/api/v1/chat/completions + method: POST + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + content_length: -1 + body: |+ + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" I've"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" used"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" mult"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"ied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"it"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":":\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" Add"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" comment"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"//"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" G"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"reeting"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" above"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" the"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" fmt"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":".Println"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" line"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" Changed"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" World"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"!\""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":" Both"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":" changes"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":" applied"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":"!\""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569107-dT7WuUmcn7VVicYiqj7M","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569107,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10467,"completion_tokens":8,"total_tokens":10475,"cost":0.0063002,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0062802,"upstream_inference_completions_cost":0.00002},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663449-ZnJKoA53WR0VmlrSmR14","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663449,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11364,"completion_tokens":41,"total_tokens":11405,"cost":0.0019673,"is_byok":false,"prompt_tokens_details":{"cached_tokens":11008,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0018648,"upstream_inference_completions_cost":0.0001025},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -174,4 +683,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 968.125709ms + duration: 2.136257792s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls.yaml index f0c2107dd0370d46cca760a6678e3330163e0983..a12b2f5d8715dcb272bff189ac74117138f3e2c2 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls.yaml @@ -24,29 +24,23 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" ."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":"Find"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":" .go files and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" files"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":" list directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" list"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":" parallel"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":" parallel"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761569532-BJhKrRGMK0C1QFlSn4Jj","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":156,"completion_tokens":10,"total_tokens":166,"cost":0.00003284,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002184,"upstream_inference_completions_cost":0.000011},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663476-aqolUhapwap8EExXBGXr","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":156,"completion_tokens":10,"total_tokens":166,"cost":0.00003284,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00002184,"upstream_inference_completions_cost":0.000011},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -55,15 +49,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.507790333s + duration: 565.017292ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44422 + content_length: 44350 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -79,31 +73,31 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"glob:0","type":"function","function":{"name":"glob"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"glob:0","type":"function","function":{"name":"glob","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"pattern"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"pattern"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":" \"**"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"**"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/*."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/*."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"id":"ls:1","type":"function","function":{"name":"ls"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"id":"ls:1","type":"function","function":{"name":"ls","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"type":"function","function":{"arguments":"{}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":1,"function":{"arguments":"{}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569532-2arbZvt7RlSBSFQNvAwa","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569532,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10945,"completion_tokens":25,"total_tokens":10970,"cost":0.0066295,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.006567,"upstream_inference_completions_cost":0.0000625},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663476-9gkVPtddVeks0FExEVxh","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663476,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10941,"completion_tokens":25,"total_tokens":10966,"cost":0.0017887,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017262,"upstream_inference_completions_cost":0.0000625},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -112,15 +106,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 4.330845166s + duration: 2.627963583s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44916 + content_length: 44844 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"ls:1\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/main.go\",\"tool_call_id\":\"glob:0\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"glob:0\",\"function\":{\"arguments\":\"{\\\"pattern\\\": \\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"ls:1\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/main.go\",\"tool_call_id\":\"glob:0\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -136,51 +130,89 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" ."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" `/"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"tmp"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"/c"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"rush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"-test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"/open"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"router"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"imi"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"-k"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"2"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"/"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"parallel"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"_calls"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"/main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"`\n\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"`\n\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"Current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"Current"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" directory"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" contains"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" contains"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":":\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":":\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":".mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":".mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569536-uFEjyiPEYOSvfBhtid2I","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569536,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10728,"completion_tokens":22,"total_tokens":10750,"cost":0.0064918,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0064368,"upstream_inference_completions_cost":0.000055},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663479-7ZznDOV7P1IGPLvbL5oJ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663479,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11044,"completion_tokens":40,"total_tokens":11084,"cost":0.001888,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001788,"upstream_inference_completions_cost":0.0001},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -189,4 +221,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 736.984542ms + duration: 3.089859s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/read_a_file.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/read_a_file.yaml index 563b98708546f7d0fc62b818069a26a92b3b47d6..251369050607cc121612c754522c93ebf0f32187 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/read_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/read_a_file.yaml @@ -24,15 +24,15 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568497-USk4g3Zshacl306I9oBr","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663339-Q5rfOJKqq0tmpcRCQk9u","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-USk4g3Zshacl306I9oBr","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":"Read"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663339-Q5rfOJKqq0tmpcRCQk9u","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":"Read"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-USk4g3Zshacl306I9oBr","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":" the go mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663339-Q5rfOJKqq0tmpcRCQk9u","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":" the go mod"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-USk4g3Zshacl306I9oBr","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663339-Q5rfOJKqq0tmpcRCQk9u","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761568497-USk4g3Zshacl306I9oBr","provider":"Hyperbolic","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":131,"completion_tokens":5,"total_tokens":136,"cost":0.0000408,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000393,"upstream_inference_completions_cost":0.0000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663339-Q5rfOJKqq0tmpcRCQk9u","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":131,"completion_tokens":5,"total_tokens":136,"cost":0.00002565,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001965,"upstream_inference_completions_cost":0.000006},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -41,15 +41,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 844.892458ms + duration: 417.198333ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44295 + content_length: 44223 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Read the go mod\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Read the go mod\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -65,57 +65,59 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.view:0","index":0,"type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"/read"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/read"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"/go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":".mod"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"/go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.view:0","type":"function","function":{"name":"","arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":".mod"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":null} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568497-rfmgDfzFvYh4d4WXEFAL","provider":"BaseTen","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568497,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10603,"completion_tokens":34,"total_tokens":10637,"cost":0.0064468,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0063618,"upstream_inference_completions_cost":0.000085},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + + data: {"id":"gen-1761663339-KKkHwVXiwKQWEuo7KYjz","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663339,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10186,"completion_tokens":34,"total_tokens":10220,"cost":0.00570396,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0056023,"upstream_inference_completions_cost":0.00010166},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -124,15 +126,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 843.624208ms + duration: 1.626690084s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44650 + content_length: 44578 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\n\",\"tool_call_id\":\"functions.view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -148,13 +150,61 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568498-ES1WmxMoSOu9tfxG9zFs","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568498,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"Your"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" module"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" file"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" shows"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":":\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" Module"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" name"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":".com"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"/test"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"project"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"`\n"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"-"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" version"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"1"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"23"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568498-ES1WmxMoSOu9tfxG9zFs","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568498,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":"`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568498-ES1WmxMoSOu9tfxG9zFs","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568498,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568498-ES1WmxMoSOu9tfxG9zFs","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568498,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10271,"completion_tokens":2,"total_tokens":10273,"cost":0.00565503,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00564905,"upstream_inference_completions_cost":0.00000598},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663341-xMEIoQ0S3Q4DhMHyWxvZ","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663357,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10993,"completion_tokens":26,"total_tokens":11019,"cost":0.0066608,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0065958,"upstream_inference_completions_cost":0.000065},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -163,4 +213,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.836452625s + duration: 10.091337834s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/simple_test.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/simple_test.yaml index 67b1a2cc8fa809d5e1ddfcd3bef5babd16ab36e6..aa9d404950f302c007afcca11d4e34ad8c5d3c05 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/simple_test.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/simple_test.yaml @@ -24,13 +24,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568496-jxAEhovCmjlDi7Et6rOR","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663336-chT2pUxbeiyfxOQHAMzY","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761568496-jxAEhovCmjlDi7Et6rOR","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663336-chT2pUxbeiyfxOQHAMzY","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761568496-jxAEhovCmjlDi7Et6rOR","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663336-chT2pUxbeiyfxOQHAMzY","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761568496-jxAEhovCmjlDi7Et6rOR","provider":"Chutes","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":128,"completion_tokens":2,"total_tokens":130,"cost":0.0000144,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000128,"upstream_inference_completions_cost":0.0000016},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663336-chT2pUxbeiyfxOQHAMzY","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":132,"completion_tokens":1,"total_tokens":133,"cost":0.0000213,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000198,"upstream_inference_completions_cost":0.0000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -39,15 +39,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.196754333s + duration: 1.08956625s - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44285 + content_length: 44213 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Hello\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"Hello\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -63,11 +63,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568496-MYySnTOUuSN0I07UWBgw","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663336-R4FtmvJiS0oJyC4uob9R","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568496-MYySnTOUuSN0I07UWBgw","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hi."},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663336-R4FtmvJiS0oJyC4uob9R","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568496-MYySnTOUuSN0I07UWBgw","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568496,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10272,"completion_tokens":2,"total_tokens":10274,"cost":0.00514,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.005136,"upstream_inference_completions_cost":0.000004},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663336-R4FtmvJiS0oJyC4uob9R","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + + data: {"id":"gen-1761663336-R4FtmvJiS0oJyC4uob9R","provider":"AtlasCloud","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663336,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10182,"completion_tokens":2,"total_tokens":10184,"cost":0.0061142,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0061092,"upstream_inference_completions_cost":0.000005},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -76,4 +78,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.109451167s + duration: 2.850610375s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool.yaml index 43670755c0ca32625f7f4dbedc2e9cb8ee23e4db..2cf87b4f85f2f733dd438de436232f014b9ec2cd 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool.yaml @@ -24,21 +24,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":"Search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":" for func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":" for func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":" main in Go repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":" main in Go repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":" using Source"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":" using Sourcegraph"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":"graph"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""} - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761569109-EIcI8HTRUgIDlaGUSD6s","provider":"Google","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569109,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":140,"completion_tokens":11,"total_tokens":151,"cost":0.0000342,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.000021,"upstream_inference_completions_cost":0.0000132},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663453-yVFjIcfB2F5uGyiOPkS6","provider":"Novita","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":144,"completion_tokens":10,"total_tokens":154,"cost":0.0000366,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000216,"upstream_inference_completions_cost":0.000015},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -47,15 +45,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 515.803333ms + duration: 847.554708ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44345 + content_length: 44273 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -71,49 +69,55 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"sourcegraph:0","type":"function","function":{"name":"sourcegraph","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":"functions.sourcegraph:0","index":0,"type":"function","function":{"name":"sourcegraph","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"query"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"{\"query"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"lang"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"lang"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" func"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"func"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" main"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" type"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" type"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"symbol"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"symbol"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" \""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"count"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"count"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":" "}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"10"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"id":null,"index":0,"type":"function","function":{"name":null,"arguments":"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"10"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569109-ZvlHXCKcLzUWtnXoehbn","provider":"Parasail","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569125,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10202,"completion_tokens":30,"total_tokens":10232,"cost":0.0057008,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0056111,"upstream_inference_completions_cost":0.0000897},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663453-jfWuyf36lvMylU4Ys36z","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663453,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10924,"completion_tokens":31,"total_tokens":10955,"cost":0.0017935,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001716,"upstream_inference_completions_cost":0.0000775},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -122,15 +126,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 10.142359292s + duration: 2.743922458s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 436 + content_length: 440 host: sourcegraph.com - body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go func main type:symbol"}}' + body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go \"func main\" type:symbol"}}' headers: Content-Type: - application/json @@ -144,21 +148,120 @@ interactions: proto_minor: 0 content_length: -1 uncompressed: true - body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/RedHatOfficial/GoCourse"},"file":{"path":"lesson2/10_defer_return_values.go","url":"/github.com/RedHatOfficial/GoCourse/-/blob/lesson2/10_defer_return_values.go","content":"package main\n\nimport \"fmt\"\n\nfunc function1() (i int) {\n\ti = 1\n\treturn\n}\n\nfunc function2() (i int) {\n\tdefer func() { i = 2 }()\n\treturn 1\n}\n\nfunc function3() (i int) {\n\tdefer func() { i += 2 }()\n\treturn 1\n}\n\nfunc main() {\n\tfmt.Printf(\"Return value of function1: %d\\n\", function1())\n\tfmt.Printf(\"Return value of function2: %d\\n\", function2())\n\tfmt.Printf(\"Return value of function3: %d\\n\", function3())\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/RedHatOfficial/GoCourse"},"file":{"path":"lesson3/01_func_type.go","url":"/github.com/RedHatOfficial/GoCourse/-/blob/lesson3/01_func_type.go","content":"package main\n\nimport \"fmt\"\n\nfunc function1() {\n\tfmt.Println(\"function1\")\n}\n\nfunc function2() {\n\tfmt.Println(\"function2\")\n}\n\nfunc main() {\n\tvar a func()\n\tfmt.Println(a)\n\n\ta = function1\n\tfmt.Println(a)\n\ta()\n\n\ta = function2\n\tfmt.Println(a)\n\ta()\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/RedHatOfficial/GoCourse"},"file":{"path":"lesson3/02_func_type.go","url":"/github.com/RedHatOfficial/GoCourse/-/blob/lesson3/02_func_type.go","content":"package main\n\nimport \"fmt\"\n\nfunc function1(x, y int) int {\n\treturn x + y\n}\n\nfunc function2(x, y int) int {\n\treturn x * y\n}\n\nfunc main() {\n\tvar a func(int, int) int\n\tfmt.Println(a)\n\n\ta = function1\n\tfmt.Println(a)\n\tfmt.Println(a(10, 20))\n\n\ta = function2\n\tfmt.Println(a)\n\tfmt.Println(a(10, 20))\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/yanfeizhang/go-training"},"file":{"path":"8-internal/memory/stackgrow/main.go","url":"/github.com/yanfeizhang/go-training/-/blob/8-internal/memory/stackgrow/main.go","content":"package main\n\nfunc main() {\n\tn := 1\n\t_ = func1(n)\n\t_ = func2(n)\n}\n\nfunc func1(n int) int {\n\t_ = make([]byte, 200)\n\treturn n\n}\n\nfunc func2(n int) int {\n\t_ = make([]byte, 20)\n\treturn n\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/unknwon/the-way-to-go_ZH_CN"},"file":{"path":"eBook/examples/chapter_6/defer.go","url":"/github.com/unknwon/the-way-to-go_ZH_CN/-/blob/eBook/examples/chapter_6/defer.go","content":"package main\n\nimport \"fmt\"\n\nfunc main() {\n\tFunction1()\n}\n\nfunc Function1() {\n\tfmt.Printf(\"In Function1 at the top\\n\")\n\tdefer Function2()\n\tfmt.Printf(\"In Function1 at the bottom!\\n\")\n}\n\nfunc Function2() {\n\tfmt.Printf(\"Function2: Deferred until the end of the calling function!\")\n}\n"},"lineMatches":[]},{"__typename":"FileMatch","repository":{"name":"github.com/Zhouchaowen/golang-tutorial"},"file":{"path":"12-library/8-error/ch_1/main.go","url":"/github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go","content":"package main\n\nimport (\n\t\"errors\"\n\t\"fmt\"\n)\n\nfunc func1() error {\n\treturn errors.New(\"func1 error\")\n}\n\nfunc func2() error {\n\treturn fmt.Errorf(\"func2 error: %w\", func1())\n}\n\nfunc main() {\n\terr := func2()\n\tif err != nil {\n\t\tfmt.Println(err)\n\t}\n}\n"},"lineMatches":[]}]}}}}' + body: '{"data":{"search":{"results":{"matchCount":0,"limitHit":false,"resultCount":0,"approximateResultCount":"0","missing":[],"timedout":[],"indexUnavailable":false,"results":[]}}}}' headers: Content-Type: - application/json status: 200 OK code: 200 - duration: 1.855203084s + duration: 1.338321167s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45869 + content_length: 44638 + host: "" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"sourcegraph:0\",\"function\":{\"arguments\":\"{\\\"query\\\": \\\"lang:go \\\\\\\"func main\\\\\\\" type:symbol\\\", \\\"count\\\": 10}\",\"name\":\"sourcegraph\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 0 matches across 0 results\\n\\nNo results found. Try a different query.\\n\",\"tool_call_id\":\"sourcegraph:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + headers: + Accept: + - application/json + Content-Type: + - application/json + User-Agent: + - OpenAI/Go 2.7.1 + url: https://openrouter.ai/api/v1/chat/completions + method: POST + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + content_length: -1 + body: |+ + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"sourcegraph:1","type":"function","function":{"name":"sourcegraph","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"query"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"lang"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" func"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"count"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" "},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"10"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663459-v1iTKywzmwtl7lQ70Wy3","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663459,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10996,"completion_tokens":26,"total_tokens":11022,"cost":0.0018242,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017592,"upstream_inference_completions_cost":0.000065},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + + data: [DONE] + + headers: + Content-Type: + - text/event-stream + status: 200 OK + code: 200 + duration: 2.274058792s +- id: 4 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 424 + host: sourcegraph.com + body: '{"query":"query Search($query: String!) { search(query: $query, version: V2, patternType: keyword ) { results { matchCount, limitHit, resultCount, approximateResultCount, missing { name }, timedout { name }, indexUnavailable, results { __typename, ... on FileMatch { repository { name }, file { path, url, content }, lineMatches { preview, lineNumber, offsetAndLengths } } } } } }","variables":{"query":"lang:go func main"}}' + headers: + Content-Type: + - application/json + User-Agent: + - crush/1.0 + url: https://sourcegraph.com/.api/graphql + method: POST + response: + proto: HTTP/2.0 + proto_major: 2 + proto_minor: 0 + content_length: -1 + uncompressed: true + body: '{"data":{"search":{"results":{"matchCount":30,"limitHit":true,"resultCount":30,"approximateResultCount":"30+","missing":[],"timedout":[],"indexUnavailable":false,"results":[{"__typename":"FileMatch","repository":{"name":"github.com/jcalabro/uscope"},"file":{"path":"assets/gobacktrace/main.go","url":"/github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go","content":"package main\n\nimport \"fmt\"\n\nfunc FuncE() {\n\tfmt.Println(\"FuncE\")\n}\n\nfunc FuncD() {\n\tFuncE()\n\tfmt.Println(\"FuncD\")\n}\n\nfunc FuncC() {\n\tFuncD()\n\tfmt.Println(\"FuncC\")\n}\n\nfunc FuncB() {\n\tFuncC()\n\tfmt.Println(\"FuncB\")\n}\n\nfunc FuncA() {\n\tFuncB()\n\tfmt.Println(\"FuncA\")\n}\n\nfunc FuncF() {\n\tfmt.Println(\"FuncF\")\n\tFuncE()\n}\n\nfunc main() {\n\tFuncA()\n\tFuncB()\n\tFuncC()\n\tFuncD()\n\tFuncE()\n\tFuncF()\n}\n"},"lineMatches":[{"preview":"func main() {","lineNumber":33,"offsetAndLengths":[[0,9]]},{"preview":"\tFuncA()","lineNumber":34,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncB()","lineNumber":35,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncC()","lineNumber":36,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncD()","lineNumber":37,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncE()","lineNumber":38,"offsetAndLengths":[[1,4]]},{"preview":"\tFuncF()","lineNumber":39,"offsetAndLengths":[[1,4]]},{"preview":"func FuncE() {","lineNumber":4,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncE\")","lineNumber":5,"offsetAndLengths":[[14,4]]},{"preview":"func FuncD() {","lineNumber":8,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncE()","lineNumber":9,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncD\")","lineNumber":10,"offsetAndLengths":[[14,4]]},{"preview":"func FuncC() {","lineNumber":13,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncD()","lineNumber":14,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncC\")","lineNumber":15,"offsetAndLengths":[[14,4]]},{"preview":"func FuncB() {","lineNumber":18,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncC()","lineNumber":19,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncB\")","lineNumber":20,"offsetAndLengths":[[14,4]]},{"preview":"func FuncA() {","lineNumber":23,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tFuncB()","lineNumber":24,"offsetAndLengths":[[1,4]]},{"preview":"\tfmt.Println(\"FuncA\")","lineNumber":25,"offsetAndLengths":[[14,4]]},{"preview":"func FuncF() {","lineNumber":28,"offsetAndLengths":[[0,4],[5,4]]},{"preview":"\tfmt.Println(\"FuncF\")","lineNumber":29,"offsetAndLengths":[[14,4]]},{"preview":"\tFuncE()","lineNumber":30,"offsetAndLengths":[[1,4]]}]}]}}}}' + headers: + Content-Type: + - application/json + status: 200 OK + code: 200 + duration: 1.226600625s +- id: 5 + request: + proto: HTTP/1.1 + proto_major: 1 + proto_minor: 1 + content_length: 52414 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.sourcegraph:0\",\"function\":{\"arguments\":\"{\\\"query\\\": \\\"lang:go func main type:symbol\\\", \\\"count\\\": 10}\",\"name\":\"sourcegraph\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n## Result 2: github.com/RedHatOfficial/GoCourse/lesson2/10_defer_return_values.go\\n\\nURL: /github.com/RedHatOfficial/GoCourse/-/blob/lesson2/10_defer_return_values.go\\n\\n## Result 3: github.com/RedHatOfficial/GoCourse/lesson3/01_func_type.go\\n\\nURL: /github.com/RedHatOfficial/GoCourse/-/blob/lesson3/01_func_type.go\\n\\n## Result 4: github.com/RedHatOfficial/GoCourse/lesson3/02_func_type.go\\n\\nURL: /github.com/RedHatOfficial/GoCourse/-/blob/lesson3/02_func_type.go\\n\\n## Result 5: github.com/yanfeizhang/go-training/8-internal/memory/stackgrow/main.go\\n\\nURL: /github.com/yanfeizhang/go-training/-/blob/8-internal/memory/stackgrow/main.go\\n\\n## Result 6: github.com/unknwon/the-way-to-go_ZH_CN/eBook/examples/chapter_6/defer.go\\n\\nURL: /github.com/unknwon/the-way-to-go_ZH_CN/-/blob/eBook/examples/chapter_6/defer.go\\n\\n## Result 7: github.com/Zhouchaowen/golang-tutorial/12-library/8-error/ch_1/main.go\\n\\nURL: /github.com/Zhouchaowen/golang-tutorial/-/blob/12-library/8-error/ch_1/main.go\\n\\n\",\"tool_call_id\":\"functions.sourcegraph:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"sourcegraph:0\",\"function\":{\"arguments\":\"{\\\"query\\\": \\\"lang:go \\\\\\\"func main\\\\\\\" type:symbol\\\", \\\"count\\\": 10}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 0 matches across 0 results\\n\\nNo results found. Try a different query.\\n\",\"tool_call_id\":\"sourcegraph:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"sourcegraph:1\",\"function\":{\"arguments\":\"{\\\"query\\\": \\\"lang:go func main\\\", \\\"count\\\": 10}\",\"name\":\"sourcegraph\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n```\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| \\tFuncB()\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n```\\n\\n```\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tfmt.Println(\\\"FuncA\\\")\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n```\\n\\n```\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| func FuncF() {\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n```\\n\\n```\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| \\tfmt.Println(\\\"FuncF\\\")\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n```\\n\\n```\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tFuncE()\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n```\\n\\n\",\"tool_call_id\":\"sourcegraph:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -174,123 +277,123 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"Found"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" "},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"30"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"30"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"+"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" matches"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" across"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" The"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" results"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"`."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" show"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" The"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" various"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" search"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" returned"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" examples"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"()`"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" various"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" implementations"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" projects"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" including"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" including"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" a"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" tutorials"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" simple"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" example"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" courses"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" github"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":".com"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" tools"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"/j"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"cal"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" The"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"ab"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" top"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"ro"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" results"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"/usc"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" include"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"ope"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" `"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"/assets"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"usc"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"/g"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"ope"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"ob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"/assets"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"ack"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"/g"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"trace"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"ob"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"/main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"ack"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"trace"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"/main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"34"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" that"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"`,"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" calls"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" Red"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" a"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" Hat"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" series"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"'s"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" of"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" Go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" functions"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" course"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" ("},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" examples"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"Func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"A"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" training"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" through"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" materials"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" Func"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":","},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"F"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" and"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":")"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" tutorial"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" in"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":" repositories"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":" sequence"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569129-nXkhVM5C2ESJnGNXvZZd","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569129,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10692,"completion_tokens":56,"total_tokens":10748,"cost":0.0043888,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0042768,"upstream_inference_completions_cost":0.000112},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663463-k7pNpdr21v43xFaLC9nw","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663463,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":13826,"completion_tokens":57,"total_tokens":13883,"cost":0.0035997,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0034572,"upstream_inference_completions_cost":0.0001425},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -299,4 +402,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 4.332189583s + duration: 2.087341583s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/update_a_file.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/update_a_file.yaml index 347e72499678619bc32a07591c2bc0b03b8084a0..b7171fd5126a1b82ef4796a2d775de6035e0756c 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/update_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/update_a_file.yaml @@ -24,27 +24,27 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":"Update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":"Update"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":" print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":" print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":" hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":" crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":" crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761568500-oqG43YqR2HxT6VT2qzEF","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.00002964,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.00001974,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663365-WDezLwg1xKSFVAbuGxk2","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":141,"completion_tokens":9,"total_tokens":150,"cost":0.000024,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000141,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -53,15 +53,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 633.531417ms + duration: 625.86275ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44351 + content_length: 44279 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -77,55 +77,61 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"ls:0","type":"function","function":{"name":"ls"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:0","type":"function","function":{"name":"view","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/update"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/update"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_a"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568500-kTBv46j9U84OciDBFvy3","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568500,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10929,"completion_tokens":31,"total_tokens":10960,"cost":0.0066349,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0065574,"upstream_inference_completions_cost":0.0000775},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663365-CI7krv4bTJLhkryU0fZf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663365,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10925,"completion_tokens":33,"total_tokens":10958,"cost":0.0017991,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017166,"upstream_inference_completions_cost":0.0000825},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -134,15 +140,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 6.423011667s + duration: 2.805592875s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44684 + content_length: 44688 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"ls:0\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\\"}\",\"name\":\"ls\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -158,61 +164,121 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"edit:1","type":"function","function":{"name":"edit","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"view:1","type":"function","function":{"name":"view"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":" \"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/update"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_a"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"old"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_string"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tf"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"mt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".Println"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/update"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"(\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"_a"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"_file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"/main"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" World"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":".go"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"!\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\")"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568508-UAkhn0YUJKmoQm7FcHCL","provider":"Novita","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568508,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11006,"completion_tokens":33,"total_tokens":11039,"cost":0.0066861,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0066036,"upstream_inference_completions_cost":0.0000825},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"new"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_string"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tf"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"mt"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".Println"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"(\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Hello"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" from"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" Crush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"!\\"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\")"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663369-d3vAMI4kBtQckNCf3UGT","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663369,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11026,"completion_tokens":63,"total_tokens":11089,"cost":0.0019347,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017772,"upstream_inference_completions_cost":0.0001575},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -221,15 +287,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 3.622929792s + duration: 2.971172916s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45093 + content_length: 45187 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"ls:0\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"view:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"edit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello from Crush!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"edit:1\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -245,11 +311,51 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568512-1wEitr8qTQQFfrRfXoJF","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568512,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"bash:2","type":"function","function":{"name":"bash","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568512-1wEitr8qTQQFfrRfXoJF","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568512,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.edit:2","function":{"arguments":"{\"file_path\": \"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\", \"new_string\": \"\\tfmt.Println(\\\"Hello from Crush!\\\")\", \"old_string\": \"\\tfmt.Println(\\\"Hello, World!\\\")\"}","name":"edit"},"type":"function"}]},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}]} + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568512-1wEitr8qTQQFfrRfXoJF","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568512,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11249,"completion_tokens":50,"total_tokens":11299,"cost":0.0057245,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0056245,"upstream_inference_completions_cost":0.0001},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"command"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" run"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" main"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"description"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" the"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" updated"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" Go"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" program"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663376-pWtbZCKmAfgcgkh2ozqk","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663376,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11136,"completion_tokens":29,"total_tokens":11165,"cost":0.0018005,"is_byok":false,"prompt_tokens_details":{"cached_tokens":11008,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001728,"upstream_inference_completions_cost":0.0000725},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -258,15 +364,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 777.590375ms + duration: 2.950160167s - id: 4 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45612 + content_length: 45532 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"ls:0\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"ls:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"view:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:1\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"functions.edit:2\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello from Crush!\\\\\\\")\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"functions.edit:2\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"view:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"view:0\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"edit:1\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\\", \\\"old_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\", \\\"new_string\\\": \\\"\\\\tfmt.Println(\\\\\\\"Hello from Crush!\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"edit:1\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"bash:2\",\"function\":{\"arguments\":\"{\\\"command\\\": \\\"go run main.go\\\", \\\"description\\\": \\\"Test the updated Go program\\\"}\",\"name\":\"bash\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"Hello from Crush!\\n\\n\\n/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/update_a_file\",\"tool_call_id\":\"bash:2\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -282,11 +388,39 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761568514-unw3yIQqfysGnDxxXWgk","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568514,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":"."},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" Updated"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" main"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":".go"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":":"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":"6"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" to"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" print"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" \""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" from"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":"!\""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568514-unw3yIQqfysGnDxxXWgk","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568514,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761568514-unw3yIQqfysGnDxxXWgk","provider":"Together","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761568514,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10802,"completion_tokens":32,"total_tokens":10834,"cost":0.010898,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.010802,"upstream_inference_completions_cost":0.000096},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663380-X3SWJMK8c3DQfq831YuQ","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663381,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11209,"completion_tokens":15,"total_tokens":11224,"cost":0.0018093,"is_byok":false,"prompt_tokens_details":{"cached_tokens":11008,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017718,"upstream_inference_completions_cost":0.0000375},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -295,4 +429,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 1.449111875s + duration: 2.006659458s diff --git a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/write_tool.yaml b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/write_tool.yaml index 73010719106597578b42733643bac1ecffbfa472..11f7705c1b65ee0eaf49a09034e2c862430c2b79 100644 --- a/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/write_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/openrouter-kimi-k2/write_tool.yaml @@ -24,25 +24,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":" config"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":"Create"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":".json"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":" config.json with name"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":" with"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":" and version data"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":" sample"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":" JSON"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":" content"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} - - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} - - data: {"id":"gen-1761569138-UOUGJFA8q0l2rD8bYeso","provider":"Parasail","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":155,"completion_tokens":8,"total_tokens":163,"cost":0.0000305,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000217,"upstream_inference_completions_cost":0.0000088},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663468-FdSBO5s1bywNMrHIsGKy","provider":"DeepInfra","model":"qwen/qwen3-next-80b-a3b-instruct","object":"chat.completion.chunk","created":1761663468,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":155,"completion_tokens":9,"total_tokens":164,"cost":0.0000316,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0000217,"upstream_inference_completions_cost":0.0000099},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -51,15 +45,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 637.56075ms + duration: 587.740334ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44388 + content_length: 44316 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -75,95 +69,101 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"write:0","type":"function","function":{"name":"write","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"functions.write:0","type":"function","function":{"name":"write","arguments":""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"{\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"{\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"file"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"content"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_path"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\":\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"{\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"/"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"name"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"tmp"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\\\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/c"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":" \\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"rush"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\\\","}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/Test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":" \\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Coder"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"version"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"Agent"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\\\":"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/open"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":" \\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"router"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"1"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"imi"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"0"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"-k"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"."}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"2"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"0"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/write"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\\\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"_tool"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"}\",\""}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"/config"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"file"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":".json"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"_path"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\":\"/"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"tmp"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"content"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"/c"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"rush"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \"{\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"-test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"name"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"/Test"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"Coder"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"Agent"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"test"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"/open"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\","},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"router"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"version"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"imi"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\":"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"-k"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":" \\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"2"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"1"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"/write"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"_tool"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"0"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"/config"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"."},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":".json"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"0"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":null,"type":"function","function":{"arguments":"\"}"}}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"\\\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":""} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}\""},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569138-OmJKq6FKzrVnsKLAoscU","provider":"SiliconFlow","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569138,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10294,"completion_tokens":51,"total_tokens":10345,"cost":0.0042196,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0041176,"upstream_inference_completions_cost":0.000102},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"function":{"arguments":"}"},"type":"function"}]},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"tool_calls","native_finish_reason":"tool_calls","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663468-CCuVCztqk1TuVZhnwWmf","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663469,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10939,"completion_tokens":53,"total_tokens":10992,"cost":0.0018575,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.001725,"upstream_inference_completions_cost":0.0001325},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -172,15 +172,15 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 3.496519166s + duration: 2.335058667s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44865 + content_length: 44776 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"functions.write:0\",\"function\":{\"arguments\":\"{\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\",\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\\"}\",\"name\":\"write\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\n\",\"tool_call_id\":\"functions.write:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\",\"cache_control\":{\"type\":\"ephemeral\"}},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"write:0\",\"function\":{\"arguments\":\"{\\\"file_path\\\": \\\"/tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\\", \\\"content\\\": \\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"role\":\"assistant\"},{\"content\":\"\\nFile successfully written: /tmp/crush-test/TestCoderAgent/openrouter-kimi-k2/write_tool/config.json\\n\",\"tool_call_id\":\"write:0\",\"role\":\"tool\"}],\"model\":\"moonshotai/kimi-k2-0905\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"usage\":{\"include\":true},\"stream\":true}" headers: Accept: - application/json @@ -196,11 +196,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"gen-1761569145-V9i0uIwXhnS2wI0TFuWF","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569145,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}]} + data: {"id":"gen-1761663474-g4fX9062GSHSboswiX6j","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663474,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} + + data: {"id":"gen-1761663474-g4fX9062GSHSboswiX6j","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663474,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569145-V9i0uIwXhnS2wI0TFuWF","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569145,"choices":[{"index":0,"delta":{"role":"assistant","content":"Done"},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}]} + data: {"id":"gen-1761663474-g4fX9062GSHSboswiX6j","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663474,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop","native_finish_reason":"stop","logprobs":null}],"system_fingerprint":"fpv0_41b1161c"} - data: {"id":"gen-1761569145-V9i0uIwXhnS2wI0TFuWF","provider":"DeepInfra","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761569145,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":10399,"completion_tokens":1,"total_tokens":10400,"cost":0.0052015,"is_byok":false,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0051995,"upstream_inference_completions_cost":0.000002},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} + data: {"id":"gen-1761663474-g4fX9062GSHSboswiX6j","provider":"Moonshot AI","model":"moonshotai/kimi-k2-0905","object":"chat.completion.chunk","created":1761663474,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null,"native_finish_reason":null,"logprobs":null}],"usage":{"prompt_tokens":11037,"completion_tokens":2,"total_tokens":11039,"cost":0.0017888,"is_byok":false,"prompt_tokens_details":{"cached_tokens":10752,"audio_tokens":0},"cost_details":{"upstream_inference_cost":null,"upstream_inference_prompt_cost":0.0017838,"upstream_inference_completions_cost":0.000005},"completion_tokens_details":{"reasoning_tokens":0,"image_tokens":0}}} data: [DONE] @@ -209,4 +211,4 @@ interactions: - text/event-stream status: 200 OK code: 200 - duration: 261.505791ms + duration: 1.965889833s diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/bash_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/bash_tool.yaml index 1ef67f0fb25050b93ff66789b8e9710e8fa241b3..991553445b9f3b98386a14bd43a683d50d20f7cf 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/bash_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/bash_tool.yaml @@ -24,21 +24,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Create"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Create"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" bash"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" bash"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" hello"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" hello"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]} - data: {"id":"2025102720501290f33650b2c3470c","created":1761569412,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":134,"completion_tokens":10,"total_tokens":144,"prompt_tokens_details":{"cached_tokens":114}}} + data: {"id":"202510282258553ebed55b95fd46eb","created":1761663535,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":134,"completion_tokens":10,"total_tokens":144,"prompt_tokens_details":{"cached_tokens":4}}} data: [DONE] @@ -47,15 +47,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 741.43025ms + duration: 576.833ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44221 + content_length: 44149 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,13 +71,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205012adfc1e8292414fa8","created":1761569412,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225855de584289cedb45ab","created":1761663535,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205012adfc1e8292414fa8","created":1761569412,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225855de584289cedb45ab","created":1761663535,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205012adfc1e8292414fa8","created":1761569412,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_41e6e471ab824667bd2e557a","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"echo 'hello bash' > test.txt\",\"description\":\"Create test.txt with content 'hello bash'\"}"}}]}}]} + data: {"id":"20251028225855de584289cedb45ab","created":1761663535,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_fc8a5f5955c042fca263a86b","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"echo 'hello bash' > test.txt\",\"description\":\"Create test.txt with content 'hello bash'\"}"}}]}}]} - data: {"id":"20251027205012adfc1e8292414fa8","created":1761569412,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10643,"completion_tokens":40,"total_tokens":10683,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225855de584289cedb45ab","created":1761663535,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10627,"completion_tokens":40,"total_tokens":10667,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -86,15 +86,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 993.531667ms + duration: 660.371625ms - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44564 + content_length: 44492 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_41e6e471ab824667bd2e557a\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"echo 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt with content 'hello bash'\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_41e6e471ab824667bd2e557a\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/bash_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use bash to create a file named test.txt with content 'hello bash'\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_fc8a5f5955c042fca263a86b\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"echo 'hello bash' > test.txt\\\",\\\"description\\\":\\\"Create test.txt with content 'hello bash'\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"no output\",\"tool_call_id\":\"call_fc8a5f5955c042fca263a86b\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -110,33 +110,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225856c6dc9a7ce8464d38","created":1761663536,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225856c6dc9a7ce8464d38","created":1761663536,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Done"}}]} + data: {"id":"20251028225856c6dc9a7ce8464d38","created":1761663536,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Done"}}]} - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" Created"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" test"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".txt"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" with"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" content"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" '"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"hello"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" bash"}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"'."}}]} - - data: {"id":"2025102720501423154863d47746bc","created":1761569414,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10691,"completion_tokens":16,"total_tokens":10707,"prompt_tokens_details":{"cached_tokens":45}}} + data: {"id":"20251028225856c6dc9a7ce8464d38","created":1761663536,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10675,"completion_tokens":6,"total_tokens":10681,"prompt_tokens_details":{"cached_tokens":10666}}} data: [DONE] @@ -145,4 +125,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.655423542s + duration: 710.481541ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/download_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/download_tool.yaml index 313b92532c27b97e7b3171cf88bcb879219bf9d4..50ee185a16fed5ffc0e44288d2a7f1e3a02cdf11 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/download_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/download_tool.yaml @@ -24,21 +24,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Download"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Download"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" save"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" save"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" example"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" example"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} - data: {"id":"2025102720501608e1f99bc5f94db3","created":1761569416,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":143,"completion_tokens":10,"total_tokens":153,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"20251028225858b7808e8d25f7447c","created":1761663538,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":143,"completion_tokens":10,"total_tokens":153,"prompt_tokens_details":{"cached_tokens":4}}} data: [DONE] @@ -47,15 +47,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 716.340625ms + duration: 671.008458ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44274 + content_length: 44202 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,13 +71,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720501703831e185f9548ed","created":1761569417,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"2025102822585850e15d253c0e4109","created":1761663538,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720501703831e185f9548ed","created":1761569417,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"2025102822585850e15d253c0e4109","created":1761663538,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720501703831e185f9548ed","created":1761569417,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_0512538ef3d9425682740765","index":0,"type":"function","function":{"name":"download","arguments":"{\"url\":\"https://example-files.online-convert.com/document/txt/example.txt\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/example.txt\"}"}}]}}]} + data: {"id":"2025102822585850e15d253c0e4109","created":1761663538,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_92e3b7db93a94e4db1179f6f","index":0,"type":"function","function":{"name":"download","arguments":"{\"url\":\"https://example-files.online-convert.com/document/txt/example.txt\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/example.txt\"}"}}]}}]} - data: {"id":"2025102720501703831e185f9548ed","created":1761569417,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10651,"completion_tokens":55,"total_tokens":10706,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"2025102822585850e15d253c0e4109","created":1761663538,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10635,"completion_tokens":55,"total_tokens":10690,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -86,7 +86,7 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 968.734083ms + duration: 783.232375ms - id: 2 request: proto: HTTP/1.1 @@ -132,15 +132,15 @@ interactions: - text/plain; charset=UTF-8 status: 200 OK code: 200 - duration: 818.156209ms + duration: 83.692417ms - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44816 + content_length: 44744 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_0512538ef3d9425682740765\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://example-files.online-convert.com/document/txt/example.txt\\\",\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/example.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_0512538ef3d9425682740765\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"download the file from https://example-files.online-convert.com/document/txt/example.txt and save it as example.txt\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_92e3b7db93a94e4db1179f6f\",\"function\":{\"arguments\":\"{\\\"url\\\":\\\"https://example-files.online-convert.com/document/txt/example.txt\\\",\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/example.txt\\\"}\",\"name\":\"download\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Successfully downloaded 2574 bytes to /tmp/crush-test/TestCoderAgent/zai-glm4.6/download_tool/example.txt (Content-Type: text/plain; charset=UTF-8)\",\"tool_call_id\":\"call_92e3b7db93a94e4db1179f6f\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -156,31 +156,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Download"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Download"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"ed"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ed"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" "}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"25"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" saved"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"7"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" as"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"4"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" example"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" bytes"}}]} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".txt"}}]} - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" to"}}]} - - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" example"}}]} - - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".txt"}}]} - - data: {"id":"20251027205019028cfe30f7194a13","created":1761569419,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10750,"completion_tokens":15,"total_tokens":10765,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225900fd23803d0ee242c1","created":1761663540,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10734,"completion_tokens":12,"total_tokens":10746,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -189,4 +183,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 929.2965ms + duration: 714.331667ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/fetch_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/fetch_tool.yaml deleted file mode 100644 index b48e49eff085c67404415f29c474dd4ba161444c..0000000000000000000000000000000000000000 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/fetch_tool.yaml +++ /dev/null @@ -1,233 +0,0 @@ ---- -version: 2 -interactions: -- id: 0 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 799 - host: "" - body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nfetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word ''John Doe''\n \n\n","role":"user"}],"model":"glm-4.5-air","max_tokens":40,"stream_options":{"include_usage":true},"stream":true}' - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.z.ai/api/coding/paas/v4/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Check"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" HTML"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" for"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" '"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"John"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Doe"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"'"}}]} - - data: {"id":"2025102720502156b782519b5040eb","created":1761569421,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":148,"completion_tokens":11,"total_tokens":159,"prompt_tokens_details":{"cached_tokens":22}}} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream;charset=UTF-8 - status: 200 OK - code: 200 - duration: 678.926875ms -- id: 1 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 44292 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.z.ai/api/coding/paas/v4/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"202510272050218c76d0ed61534be1","created":1761569421,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"202510272050218c76d0ed61534be1","created":1761569421,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"202510272050218c76d0ed61534be1","created":1761569421,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_06c0b4d3fb834cfc81b16ee1","index":0,"type":"function","function":{"name":"fetch","arguments":"{\"format\":\"text\",\"url\":\"https://example-files.online-convert.com/website/html/example.html\"}"}}]}}]} - - data: {"id":"202510272050218c76d0ed61534be1","created":1761569421,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10658,"completion_tokens":37,"total_tokens":10695,"prompt_tokens_details":{"cached_tokens":43}}} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream;charset=UTF-8 - status: 200 OK - code: 200 - duration: 1.497144416s -- id: 2 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 0 - host: example-files.online-convert.com - headers: - User-Agent: - - crush/1.0 - url: https://example-files.online-convert.com/website/html/example.html - method: GET - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - uncompressed: true - body: |- - - - - - -

HTML test file

- -

Purpose: Provide example of this file type
- Document file type: HTML
- Version: 1.0
- Remark:

- -

- - Example content:
- The names "John Doe" for males, "Jane Doe" or "Jane Roe" for females, or "Jonnie Doe" and "Janie Doe" for children, or just "Doe" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of "John Doe" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand.

- -

John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series.

- -

Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, "John Doe v. Jane Roe". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) "John Doe"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases.

- -

- - File created by https://www.online-convert.com
- More example files: https://www.online-convert.com/file-type
- Text of "Example content": Wikipedia
- License: Attribution-ShareAlike 3.0 Unported - -

- -

Feel free to use and share the file according to license above.

- - - - headers: - Content-Type: - - text/html; charset=UTF-8 - status: 200 OK - code: 200 - duration: 217.718209ms -- id: 3 - request: - proto: HTTP/1.1 - proto_major: 1 - proto_minor: 1 - content_length: 47124 - host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/fetch_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"fetch the content from https://example-files.online-convert.com/website/html/example.html and tell me if it contains the word 'John Doe'\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_06c0b4d3fb834cfc81b16ee1\",\"function\":{\"arguments\":\"{\\\"format\\\":\\\"text\\\",\\\"url\\\":\\\"https://example-files.online-convert.com/website/html/example.html\\\"}\",\"name\":\"fetch\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"HTML test file Purpose: Provide example of this file type Document file type: HTML Version: 1.0 Remark: Example content: The names \\\"John Doe\\\" for males, \\\"Jane Doe\\\" or \\\"Jane Roe\\\" for females, or \\\"Jonnie Doe\\\" and \\\"Janie Doe\\\" for children, or just \\\"Doe\\\" non-gender-specifically are used as placeholder names for a party whose true identity is unknown or must be withheld in a legal action, case, or discussion. The names are also used to refer to acorpse or hospital patient whose identity is unknown. This practice is widely used in the United States and Canada, but is rarely used in other English-speaking countries including the United Kingdom itself, from where the use of \\\"John Doe\\\" in a legal context originates. The names Joe Bloggs or John Smith are used in the UK instead, as well as in Australia and New Zealand. John Doe is sometimes used to refer to a typical male in other contexts as well, in a similar manner to John Q. Public, known in Great Britain as Joe Public, John Smith or Joe Bloggs. For example, the first name listed on a form is often John Doe, along with a fictional address or other fictional information to provide an example of how to fill in the form. The name is also used frequently in popular culture, for example in the Frank Capra film Meet John Doe. John Doe was also the name of a 2002 American television series. Similarly, a child or baby whose identity is unknown may be referred to as Baby Doe. A notorious murder case in Kansas City, Missouri, referred to the baby victim as Precious Doe. Other unidentified female murder victims are Cali Doe and Princess Doe. Additional persons may be called James Doe, Judy Doe, etc. However, to avoid possible confusion, if two anonymous or unknown parties are cited in a specific case or action, the surnames Doe and Roe may be used simultaneously; for example, \\\"John Doe v. Jane Roe\\\". If several anonymous parties are referenced, they may simply be labelled John Doe #1, John Doe #2, etc. (the U.S. Operation Delego cited 21 (numbered) \\\"John Doe\\\"s) or labelled with other variants of Doe / Roe / Poe / etc. Other early alternatives such as John Stiles and Richard Miles are now rarely used, and Mary Major has been used in some American federal cases. File created by https://www.online-convert.com More example files: https://www.online-convert.com/file-type Text of \\\"Example content\\\": Wikipedia License: Attribution-ShareAlike 3.0 Unported Feel free to use and share the file according to license above.\",\"tool_call_id\":\"call_06c0b4d3fb834cfc81b16ee1\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" - headers: - Accept: - - application/json - Content-Type: - - application/json - User-Agent: - - OpenAI/Go 2.7.1 - url: https://api.z.ai/api/coding/paas/v4/chat/completions - method: POST - response: - proto: HTTP/2.0 - proto_major: 2 - proto_minor: 0 - content_length: -1 - body: |+ - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Yes"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" content"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" contains"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" word"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" \""}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"John"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" Doe"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\""}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" multiple"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" times"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" throughout"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" text"}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} - - data: {"id":"202510272050237a17f5fa4fad4021","created":1761569423,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":11252,"completion_tokens":22,"total_tokens":11274,"prompt_tokens_details":{"cached_tokens":10595}}} - - data: [DONE] - - headers: - Content-Type: - - text/event-stream;charset=UTF-8 - status: 200 OK - code: 200 - duration: 940.009042ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/glob_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/glob_tool.yaml index 8070e63e92b0d3bfe5c6620478b7c1a098d07e6e..dd2f2b0f0b8a33dfaca9e4b066327da54a77b05b 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/glob_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/glob_tool.yaml @@ -24,19 +24,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Find"}}]} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Find"}}]} - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" all"}}]} - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]} - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" glob"}}]} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} - data: {"id":"20251027205025492b71cfe2ba4b8f","created":1761569425,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":132,"completion_tokens":9,"total_tokens":141,"prompt_tokens_details":{"cached_tokens":22}}} + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" glob"}}]} + + data: {"id":"202510282259141882a6e5c66c4a52","created":1761663554,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":132,"completion_tokens":10,"total_tokens":142,"prompt_tokens_details":{"cached_tokens":114}}} data: [DONE] @@ -45,15 +47,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 584.032791ms + duration: 935.680041ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44210 + content_length: 44138 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -69,133 +71,153 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" all"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" all"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" This"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ."}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" is"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" straightforward"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" request"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":":\n\n"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"1"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Use"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" function"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" with"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" with"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" pattern"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" pattern"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \"*."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \"*."}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\""}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\""}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" all"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Go"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Go"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" The"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"2"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" path"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parameter"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" The"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" is"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" path"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" optional"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parameter"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" and"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" can"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" defaults"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" be"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" omitted"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" since"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" it"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" working"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" defaults"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" so"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" working"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" don"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n\n"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'t"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Let"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" make"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" specify"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" it"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" call"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_7fcd84b2d20f462496b6f14a","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"*.go\"}"}}]}}]} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720502540463c86c27e449a","created":1761569425,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10641,"completion_tokens":78,"total_tokens":10719,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_e48fa09a1f4e43f796145c00","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"*.go\"}"}}]}}]} + + data: {"id":"20251028225914b1815711dc8e421b","created":1761663554,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10625,"completion_tokens":88,"total_tokens":10713,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -204,15 +226,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 964.920541ms + duration: 650.744167ms - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44517 + content_length: 44445 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_7fcd84b2d20f462496b6f14a\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool/main.go\",\"tool_call_id\":\"call_7fcd84b2d20f462496b6f14a\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files in the current directory\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_e48fa09a1f4e43f796145c00\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/glob_tool/main.go\",\"tool_call_id\":\"call_e48fa09a1f4e43f796145c00\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -228,33 +250,49 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/tmp"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/c"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"rush"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-test"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/Test"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Coder"}}]} + + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Agent"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/z"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Found"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"ai"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" "}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-g"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"1"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"lm"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" ."}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"4"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"go"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" file"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"6"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":":"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/g"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" `"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"lob"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"main"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"_tool"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/main"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"`"}}]} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"20251027205027860ba0540df243fa","created":1761569427,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10684,"completion_tokens":16,"total_tokens":10700,"prompt_tokens_details":{"cached_tokens":10643}}} + data: {"id":"202510282259156d9acfc59a144376","created":1761663555,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10668,"completion_tokens":24,"total_tokens":10692,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -263,4 +301,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.648606042s + duration: 1.423900375s diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/grep_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/grep_tool.yaml index 1f9b05923e5af6d6d97ecdf86a2dc89bea4ea9a1..ccf5469a9d3804c3f4839a11f559bc32afbcdaf2 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/grep_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/grep_tool.yaml @@ -24,17 +24,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205029e5e7d6f4bced48d2","created":1761569430,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205029e5e7d6f4bced48d2","created":1761569430,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"grep"}}]} + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"grep"}}]} - data: {"id":"20251027205029e5e7d6f4bced48d2","created":1761569430,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" package"}}]} + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" package"}}]} - data: {"id":"20251027205029e5e7d6f4bced48d2","created":1761569430,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" go"}}]} + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" in"}}]} - data: {"id":"20251027205029e5e7d6f4bced48d2","created":1761569430,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]} + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" go"}}]} - data: {"id":"20251027205029e5e7d6f4bced48d2","created":1761569430,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":133,"completion_tokens":8,"total_tokens":141,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]} + + data: {"id":"20251028225921ff8e208942d540d2","created":1761663561,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":133,"completion_tokens":9,"total_tokens":142,"prompt_tokens_details":{"cached_tokens":4}}} data: [DONE] @@ -43,15 +45,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 592.670875ms + duration: 566.837833ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44208 + content_length: 44136 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -67,13 +69,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720503098caff55ec794e7a","created":1761569430,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225921617c057f76df41ef","created":1761663561,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720503098caff55ec794e7a","created":1761569430,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225921617c057f76df41ef","created":1761663561,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720503098caff55ec794e7a","created":1761569430,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_242c409f86954d2e940fd26e","index":0,"type":"function","function":{"name":"grep","arguments":"{\"include\":\"*.go\",\"pattern\":\"package\"}"}}]}}]} + data: {"id":"20251028225921617c057f76df41ef","created":1761663561,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_24ae82d2333b49b0ad0687c6","index":0,"type":"function","function":{"name":"grep","arguments":"{\"include\":\"*.go\",\"pattern\":\"package\"}"}}]}}]} - data: {"id":"2025102720503098caff55ec794e7a","created":1761569430,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10642,"completion_tokens":26,"total_tokens":10668,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225921617c057f76df41ef","created":1761663561,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10626,"completion_tokens":26,"total_tokens":10652,"prompt_tokens_details":{"cached_tokens":10580}}} data: [DONE] @@ -82,15 +84,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 954.222458ms + duration: 667.12125ms - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44591 + content_length: 44519 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_242c409f86954d2e940fd26e\",\"function\":{\"arguments\":\"{\\\"include\\\":\\\"*.go\\\",\\\"pattern\\\":\\\"package\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/zai-glm4.6/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_242c409f86954d2e940fd26e\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/grep_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use grep to search for the word 'package' in go files\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_24ae82d2333b49b0ad0687c6\",\"function\":{\"arguments\":\"{\\\"include\\\":\\\"*.go\\\",\\\"pattern\\\":\\\"package\\\"}\",\"name\":\"grep\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Found 1 matches\\n/tmp/crush-test/TestCoderAgent/zai-glm4.6/grep_tool/main.go:\\n Line 1, Char 1: package main\\n\",\"tool_call_id\":\"call_24ae82d2333b49b0ad0687c6\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -106,77 +108,43 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Found"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" "}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"1"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" match"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":":"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" `/"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"tmp"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"/c"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"rush"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"-test"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"/Test"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Coder"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Agent"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"/z"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"ai"}}]} - - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"-g"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"lm"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"4"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Found"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" "}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"6"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"1"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"/g"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" match"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"rep"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" in"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"_tool"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" `"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"/main"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"main"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":":"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":":"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"1"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"1"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"`"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"`"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" contains"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" -"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" `"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" `"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"package"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"package"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"`"}}]} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"`"}}]} - data: {"id":"202510272050311b5579c8dcb14251","created":1761569431,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10710,"completion_tokens":38,"total_tokens":10748,"prompt_tokens_details":{"cached_tokens":10596}}} + data: {"id":"20251028225922be006f9fca0e4676","created":1761663562,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10694,"completion_tokens":21,"total_tokens":10715,"prompt_tokens_details":{"cached_tokens":10651}}} data: [DONE] @@ -185,4 +153,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.344232417s + duration: 1.377471625s diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/ls_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/ls_tool.yaml index 80dd7107c16b716587e616657f14f7b0731b5b64..adacd0361474f51e24ea7da58ad29bb7132ffdc1 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/ls_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/ls_tool.yaml @@ -24,19 +24,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"List"}}]} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"List"}}]} - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" files"}}]} - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" ls"}}]} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" ls"}}]} - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" command"}}]} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" command"}}]} - data: {"id":"2025102720503367476e2233674d0c","created":1761569433,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":130,"completion_tokens":9,"total_tokens":139,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"202510282259249c24d6a539d34fa4","created":1761663564,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":130,"completion_tokens":9,"total_tokens":139,"prompt_tokens_details":{"cached_tokens":115}}} data: [DONE] @@ -45,15 +45,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 651.609917ms + duration: 746.722333ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44202 + content_length: 44130 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -69,13 +69,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050349bfb7dabd8804dd6","created":1761569434,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282259250a666966d1d54d83","created":1761663565,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272050349bfb7dabd8804dd6","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259250a666966d1d54d83","created":1761663565,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"202510272050349bfb7dabd8804dd6","created":1761569434,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_8789ae4d0e38417ea2423cbe","index":0,"type":"function","function":{"name":"ls","arguments":"{}"}}]}}]} + data: {"id":"202510282259250a666966d1d54d83","created":1761663565,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_c69851fefa134668ba3611c1","index":0,"type":"function","function":{"name":"ls","arguments":"{\"path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool\"}"}}]}}]} - data: {"id":"202510272050349bfb7dabd8804dd6","created":1761569434,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10639,"completion_tokens":9,"total_tokens":10648,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282259250a666966d1d54d83","created":1761663565,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10623,"completion_tokens":33,"total_tokens":10656,"prompt_tokens_details":{"cached_tokens":43}}} data: [DONE] @@ -84,15 +84,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 947.258916ms + duration: 2.1793745s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44509 + content_length: 44499 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_8789ae4d0e38417ea2423cbe\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_8789ae4d0e38417ea2423cbe\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use ls to list the files in the current directory\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_c69851fefa134668ba3611c1\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/zai-glm4.6/ls_tool/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_c69851fefa134668ba3611c1\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -108,21 +108,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"go"}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"go"}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".mod"}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".mod"}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"2025102720503438b290d7b6214b2b","created":1761569434,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10683,"completion_tokens":10,"total_tokens":10693,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282259276c55fb550f8d41f7","created":1761663567,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10691,"completion_tokens":10,"total_tokens":10701,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -131,4 +131,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 796.619208ms + duration: 1.01095175s diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/multiedit_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/multiedit_tool.yaml index 6b340e79860374aaff5916191bf3de46d257af9c..f24af44d33dcc9b43fbce7986147297f984b9b85 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/multiedit_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/multiedit_tool.yaml @@ -24,21 +24,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Mult"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Mult"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"ied"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"ied"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"it"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"it"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" code"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Code"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" modification"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Modification"}}]} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" request"}}]} - data: {"id":"2025102720503657170e9c8cbd43dc","created":1761569436,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":153,"completion_tokens":10,"total_tokens":163,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"20251028225928a02e3f15bfe14c6a","created":1761663568,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":153,"completion_tokens":10,"total_tokens":163,"prompt_tokens_details":{"cached_tokens":115}}} data: [DONE] @@ -47,15 +47,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 594.973125ms + duration: 685.060333ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44288 + content_length: 44216 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,67 +71,149 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"I"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"'ll"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" use"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" mult"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"ied"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"it"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" to"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" mult"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" make"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"ied"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" both"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"it"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" changes"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" to"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":":\n"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"1"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" First"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Change"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" '"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" let"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Hello"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" me"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" read"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" World"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"!'"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" file"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" to"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" '"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" see"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Hello"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" its"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" current"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Crush"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" state"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"!'\n"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".\n"}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"2"}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_f8cc93c1836546db9104597e","index":0,"type":"function","function":{"name":"view","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\"}"}}]}}]} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"2025102720503712887b521b844d5c","created":1761569437,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10664,"completion_tokens":65,"total_tokens":10729,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Add"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" comment"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" '//"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" G"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"reeting"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" above"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" fmt"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".Println"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" line"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n\n"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"First"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" read"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" see"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" content"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" and"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" understand"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" exact"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" formatting"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" and"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" indentation"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_a6915eda77d14eb1a2a02982","index":0,"type":"function","function":{"name":"view","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\"}"}}]}}]} + + data: {"id":"20251028225928f800abfa305d4d5d","created":1761663568,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10648,"completion_tokens":106,"total_tokens":10754,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -140,15 +222,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.599562s + duration: 630.192333ms - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44857 + content_length: 44678 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"\\nI'll use multiedit to make both changes to main.go. First, let me read the file to see its current state.\\n\",\"tool_calls\":[{\"id\":\"call_f8cc93c1836546db9104597e\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_f8cc93c1836546db9104597e\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_a6915eda77d14eb1a2a02982\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_a6915eda77d14eb1a2a02982\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -164,45 +246,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Now"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" I"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"'ll"}}]} + data: {"id":"202510282259302329ae1387054692","created":1761663570,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" use"}}]} + data: {"id":"202510282259302329ae1387054692","created":1761663570,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" mult"}}]} + data: {"id":"202510282259302329ae1387054692","created":1761663570,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_8695f45b2ab845c199121578","index":0,"type":"function","function":{"name":"multiedit","arguments":"{\"edits\":[{\"new_string\": \"func main() {\\n\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\\n}\", \"old_string\": \"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"}],\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\"}"}}]}}]} - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"ied"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"it"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" to"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" change"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" text"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" and"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" add"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" comment"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":":\n"}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_c1d8ac4c960c4f4b942dca36","index":0,"type":"function","function":{"name":"multiedit","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\",\"edits\":[{\"old_string\": \"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\", \"new_string\": \"func main() {\\n\\t// Greeting\\n\\tfmt.Println(\\\"Hello, Crush!\\\")\\n}\"}]}"}}]}}]} - - data: {"id":"2025102720503951eb0db67ae844db","created":1761569439,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10786,"completion_tokens":116,"total_tokens":10902,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282259302329ae1387054692","created":1761663570,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10743,"completion_tokens":100,"total_tokens":10843,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -211,15 +261,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 933.422958ms + duration: 827.610458ms - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45536 + content_length: 45293 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"\\nI'll use multiedit to make both changes to main.go. First, let me read the file to see its current state.\\n\",\"tool_calls\":[{\"id\":\"call_f8cc93c1836546db9104597e\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_f8cc93c1836546db9104597e\",\"role\":\"tool\"},{\"content\":\"\\nNow I'll use multiedit to change the text and add the comment:\\n\",\"tool_calls\":[{\"id\":\"call_c1d8ac4c960c4f4b942dca36\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\\",\\\"edits\\\":[{\\\"old_string\\\": \\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\", \\\"new_string\\\": \\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\"}]}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"call_c1d8ac4c960c4f4b942dca36\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use multiedit to change 'Hello, World!' to 'Hello, Crush!' and add a comment '// Greeting' above the fmt.Println line in main.go\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_a6915eda77d14eb1a2a02982\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_a6915eda77d14eb1a2a02982\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_8695f45b2ab845c199121578\",\"function\":{\"arguments\":\"{\\\"edits\\\":[{\\\"new_string\\\": \\\"func main() {\\\\n\\\\t// Greeting\\\\n\\\\tfmt.Println(\\\\\\\"Hello, Crush!\\\\\\\")\\\\n}\\\", \\\"old_string\\\": \\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\"}],\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\\"}\",\"name\":\"multiedit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nApplied 1 edits to file: /tmp/crush-test/TestCoderAgent/zai-glm4.6/multiedit_tool/main.go\\n\\n\",\"tool_call_id\":\"call_8695f45b2ab845c199121578\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -235,65 +285,69 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} + + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Done"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Done"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Changed"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"!"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" '"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" Changed"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" \""}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Hello"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" World"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"!'"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" World"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" to"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"!\""}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" '"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" to"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" \""}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":","}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Hello"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Crush"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"!'"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" Crush"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"!\""}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" added"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" and"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" '//"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" added"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" G"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" \"//"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"reeting"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" G"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"'"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"reeting"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" comment"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\""}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" in"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" comment"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" above"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" the"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":":"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" fmt"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"5"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".Println"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"-"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" line"}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"6"}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"2025102720504144e1130174c347eb","created":1761569441,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10943,"completion_tokens":32,"total_tokens":10975,"prompt_tokens_details":{"cached_tokens":10728}}} + data: {"id":"2025102822593144b780ac4ea448bf","created":1761663571,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10884,"completion_tokens":34,"total_tokens":10918,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -302,4 +356,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 920.396167ms + duration: 10.714352666s diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/parallel_tool_calls.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/parallel_tool_calls.yaml index 5c48d32290b22bc7e28f45661d784c64d64cfeae..275934123b027e27d7c1505249c68be9ba60602f 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/parallel_tool_calls.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/parallel_tool_calls.yaml @@ -24,19 +24,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Parallel"}}]} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Parallel"}}]} - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" glob"}}]} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" glob"}}]} - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" ls"}}]} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" ls"}}]} - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" commands"}}]} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" commands"}}]} - data: {"id":"20251027205052437e68155be84b62","created":1761569452,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":149,"completion_tokens":9,"total_tokens":158,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"202510282259507b4c984ee9aa4ff2","created":1761663590,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":149,"completion_tokens":9,"total_tokens":158,"prompt_tokens_details":{"cached_tokens":122}}} data: [DONE] @@ -45,15 +45,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 819.570959ms + duration: 667.117209ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44299 + content_length: 44227 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -69,237 +69,133 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":":\n"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":":\n"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"1"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"1"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Use"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Use"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" all"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" all"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ."}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ."}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \n"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"2"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"2"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Use"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Use"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ls"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ls"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" list"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" list"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"3"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"3"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Run"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Run"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" both"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" both"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" calls"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" calls"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parallel"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parallel"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n\n"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n\n"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"This"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"I"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" is"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" straightforward"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" -"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" both"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tools"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" both"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" single"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" message"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" and"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" run"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ls"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" them"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tools"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parallel"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" same"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Let"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" message"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" make"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" The"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" specifically"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" calls"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" emphasized"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" running"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" them"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_90c4d294870442d49800c870","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"**/*.go\"}"}}]}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_95f4a5a97f3c4b0987e5e6be","index":1,"type":"function","function":{"name":"ls","arguments":"{\"path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls\"}"}}]}}]} - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parallel"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" so"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" should"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" make"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" both"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tool"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" calls"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" one"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" message"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".\n\n"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"For"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" glob"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" use"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" pattern"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \"*."}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\""}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" all"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Go"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".\n"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"For"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ls"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" don"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'t"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" any"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" parameters"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" since"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" it"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" defaults"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" working"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_6bd5dfa479d14511a40151b4","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"*.go\"}"}}]}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":3,"delta":{"tool_calls":[{"id":"call_a3ad9fccf0804ca6bb750ba8","index":1,"type":"function","function":{"name":"ls","arguments":"{}"}}]}}]} - - data: {"id":"20251027205053e30bf5a5f80e46bb","created":1761569453,"model":"glm-4.6","choices":[{"index":4,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10659,"completion_tokens":134,"total_tokens":10793,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225950ce1e99bff28a4df4","created":1761663590,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10643,"completion_tokens":108,"total_tokens":10751,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -308,15 +204,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.979062208s + duration: 604.815916ms - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44884 + content_length: 44889 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_6bd5dfa479d14511a40151b4\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_a3ad9fccf0804ca6bb750ba8\",\"function\":{\"arguments\":\"{}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_6bd5dfa479d14511a40151b4\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_a3ad9fccf0804ca6bb750ba8\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use glob to find all .go files and use ls to list the current directory, it is very important that you run both tool calls in parallel\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_90c4d294870442d49800c870\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/*.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"},{\"id\":\"call_95f4a5a97f3c4b0987e5e6be\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls/main.go\",\"tool_call_id\":\"call_90c4d294870442d49800c870\",\"role\":\"tool\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/zai-glm4.6/parallel_tool_calls/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_95f4a5a97f3c4b0987e5e6be\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -332,49 +228,47 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Found"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" "}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Found"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"1"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" "}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" ."}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"1"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"go"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" ."}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" file"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"go"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":":"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":":"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Current"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" directory"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Current"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" contains"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" directory"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":":"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" contains"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" go"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" go"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".mod"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".mod"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"2025102720505663446e1552704966","created":1761569456,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10743,"completion_tokens":24,"total_tokens":10767,"prompt_tokens_details":{"cached_tokens":10661}}} + data: {"id":"20251028225952e294f5b79e4849c6","created":1761663592,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10753,"completion_tokens":23,"total_tokens":10776,"prompt_tokens_details":{"cached_tokens":10645}}} data: [DONE] @@ -383,4 +277,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 939.501583ms + duration: 690.978584ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/read_a_file.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/read_a_file.yaml index 6c59c5169c7823095229e244dd085b67af8b906d..69782544502a49926b4533194fab299a940bcf3f 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/read_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/read_a_file.yaml @@ -24,15 +24,15 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027204955d48a37603ec04109","created":1761569395,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225806518c6376c29b42d8","created":1761663487,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027204955d48a37603ec04109","created":1761569395,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Go"}}]} + data: {"id":"20251028225806518c6376c29b42d8","created":1761663487,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Go"}}]} - data: {"id":"20251027204955d48a37603ec04109","created":1761569395,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" mod"}}]} + data: {"id":"20251028225806518c6376c29b42d8","created":1761663487,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" mod"}}]} - data: {"id":"20251027204955d48a37603ec04109","created":1761569395,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]} + data: {"id":"20251028225806518c6376c29b42d8","created":1761663487,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" read"}}]} - data: {"id":"20251027204955d48a37603ec04109","created":1761569395,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":124,"completion_tokens":7,"total_tokens":131,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"20251028225806518c6376c29b42d8","created":1761663487,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":124,"completion_tokens":7,"total_tokens":131,"prompt_tokens_details":{"cached_tokens":114}}} data: [DONE] @@ -41,15 +41,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 586.295459ms + duration: 563.050625ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44172 + content_length: 44100 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -65,13 +65,155 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272049559ff326d0c4804598","created":1761569396,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272049559ff326d0c4804598","created":1761569396,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} - data: {"id":"202510272049559ff326d0c4804598","created":1761569396,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_6b0816a9a9334dd5b2689d93","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"go.mod\"}"}}]}}]} + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} - data: {"id":"202510272049559ff326d0c4804598","created":1761569396,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10633,"completion_tokens":18,"total_tokens":10651,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" read"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" go"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" mod"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" This"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" is"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" typically"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" `"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"go"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".mod"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"`"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Go"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" project"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" first"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" check"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" what"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" are"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" available"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" go"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".mod"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" then"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" read"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" its"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" contents"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".\n\n"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Let"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" start"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" by"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" listing"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" files"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" see"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" if"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" there"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'s"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" go"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".mod"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_d2b1319d790e410b8fd7ece6","index":0,"type":"function","function":{"name":"ls","arguments":"{\"path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\"}"}}]}}]} + + data: {"id":"202510282258074fca18a4bc684551","created":1761663487,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10617,"completion_tokens":104,"total_tokens":10721,"prompt_tokens_details":{"cached_tokens":45}}} data: [DONE] @@ -80,15 +222,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 950.527666ms + duration: 3.636547083s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44482 + content_length: 44477 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_6b0816a9a9334dd5b2689d93\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"go.mod\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/go.mod\",\"tool_call_id\":\"call_6b0816a9a9334dd5b2689d93\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_d2b1319d790e410b8fd7ece6\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_d2b1319d790e410b8fd7ece6\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -104,13 +246,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720495749538285d9d94d50","created":1761569397,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225814b3fc6d6a7d71410b","created":1761663495,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720495749538285d9d94d50","created":1761569397,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225814b3fc6d6a7d71410b","created":1761663495,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720495749538285d9d94d50","created":1761569397,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_f8c650cf7f374fc4b059bb22","index":0,"type":"function","function":{"name":"view","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/go.mod\"}"}}]}}]} + data: {"id":"20251028225814b3fc6d6a7d71410b","created":1761663495,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_abc89496fbf4431aa7a18349","index":0,"type":"function","function":{"name":"view","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/go.mod\"}"}}]}}]} - data: {"id":"2025102720495749538285d9d94d50","created":1761569397,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10676,"completion_tokens":36,"total_tokens":10712,"prompt_tokens_details":{"cached_tokens":45}}} + data: {"id":"20251028225814b3fc6d6a7d71410b","created":1761663495,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10685,"completion_tokens":36,"total_tokens":10721,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -119,15 +261,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.473317542s + duration: 3.977741917s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44869 + content_length: 44864 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_6b0816a9a9334dd5b2689d93\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"go.mod\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/go.mod\",\"tool_call_id\":\"call_6b0816a9a9334dd5b2689d93\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_f8c650cf7f374fc4b059bb22\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\n\",\"tool_call_id\":\"call_f8c650cf7f374fc4b059bb22\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Read the go mod\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_d2b1319d790e410b8fd7ece6\",\"function\":{\"arguments\":\"{\\\"path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file\\\"}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/\\n - go.mod\\n - main.go\\n\",\"tool_call_id\":\"call_d2b1319d790e410b8fd7ece6\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_abc89496fbf4431aa7a18349\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/read_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|module example.com/testproject\\n 2|\\n 3|go 1.23\\n\\n\",\"tool_call_id\":\"call_abc89496fbf4431aa7a18349\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -143,41 +285,33 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"``"}}]} - - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"`\n"}}]} - - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"module"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" example"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".com"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"module"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"/test"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" example"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"project"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".com"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n\n"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"/test"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"go"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"project"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" "}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"1"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"go"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" "}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"23"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"1"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"```"}}]} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"23"}}]} - data: {"id":"2025102720500090963b7efad0449a","created":1761569400,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10747,"completion_tokens":20,"total_tokens":10767,"prompt_tokens_details":{"cached_tokens":10711}}} + data: {"id":"2025102822581992bf77a303e04c61","created":1761663499,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10756,"completion_tokens":16,"total_tokens":10772,"prompt_tokens_details":{"cached_tokens":10720}}} data: [DONE] @@ -186,4 +320,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.028043875s + duration: 682.688792ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/simple_test.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/simple_test.yaml index 7b168505ee38e91b8fae294ee106bb3c54b28e91..3fd0d234edf1c01a4168d2b99f739f6761700668 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/simple_test.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/simple_test.yaml @@ -24,13 +24,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720495318d6029e0f5d4e8e","created":1761569393,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225804960ed04de2a34ff6","created":1761663484,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720495318d6029e0f5d4e8e","created":1761569393,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Simple"}}]} + data: {"id":"20251028225804960ed04de2a34ff6","created":1761663484,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Simple"}}]} - data: {"id":"2025102720495318d6029e0f5d4e8e","created":1761569393,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" greeting"}}]} + data: {"id":"20251028225804960ed04de2a34ff6","created":1761663484,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" greeting"}}]} - data: {"id":"2025102720495318d6029e0f5d4e8e","created":1761569393,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":121,"completion_tokens":6,"total_tokens":127,"prompt_tokens_details":{"cached_tokens":22}}} + data: {"id":"20251028225804960ed04de2a34ff6","created":1761663484,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":121,"completion_tokens":6,"total_tokens":127,"prompt_tokens_details":{"cached_tokens":4}}} data: [DONE] @@ -39,15 +39,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.6131245s + duration: 1.431727375s - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44162 + content_length: 44090 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/simple_test\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"Hello\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -63,29 +63,29 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Hello"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"!"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"!"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" How"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" How"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" can"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" can"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" I"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" I"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" help"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" help"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" you"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" you"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" today"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" today"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"?"}}]} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"?"}}]} - data: {"id":"20251027204953660597e20b3d46f0","created":1761569393,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10629,"completion_tokens":14,"total_tokens":10643,"prompt_tokens_details":{"cached_tokens":45}}} + data: {"id":"2025102822580569bb1503642e4d8b","created":1761663485,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10613,"completion_tokens":14,"total_tokens":10627,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -94,4 +94,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 2.258562625s + duration: 1.941200208s diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/sourcegraph_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/sourcegraph_tool.yaml index 1c08a292ea1214ab0a381aa651c200afe5da1922..510b3c9da9f7cf4367cacf3fb9fec8b154c770a0 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/sourcegraph_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/sourcegraph_tool.yaml @@ -24,21 +24,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Source"}}]} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"search"}}]} - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"graph"}}]} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" func"}}]} - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" in"}}]} - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" function"}}]} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" search"}}]} - - data: {"id":"20251027205043a4b6149f14264e9a","created":1761569443,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":133,"completion_tokens":10,"total_tokens":143,"prompt_tokens_details":{"cached_tokens":114}}} + data: {"id":"20251028225943469524737f404ad1","created":1761663583,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":133,"completion_tokens":9,"total_tokens":142,"prompt_tokens_details":{"cached_tokens":115}}} data: [DONE] @@ -47,15 +45,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 677.8505ms + duration: 634.14525ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44222 + content_length: 44150 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,13 +69,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720504341e46ce57b0d43c4","created":1761569443,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225943603311c911f04425","created":1761663583,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720504341e46ce57b0d43c4","created":1761569443,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225943603311c911f04425","created":1761663583,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720504341e46ce57b0d43c4","created":1761569443,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_c1c1d9c4d3814512a37b5ad4","index":0,"type":"function","function":{"name":"sourcegraph","arguments":"{\"query\":\"lang:go func main\",\"count\":10}"}}]}}]} + data: {"id":"20251028225943603311c911f04425","created":1761663583,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_2373c4cfefc140738398b8e6","index":0,"type":"function","function":{"name":"sourcegraph","arguments":"{\"query\":\"lang:go func main\"}"}}]}}]} - data: {"id":"2025102720504341e46ce57b0d43c4","created":1761569443,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10642,"completion_tokens":30,"total_tokens":10672,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"20251028225943603311c911f04425","created":1761663583,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10626,"completion_tokens":22,"total_tokens":10648,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -86,7 +84,7 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 964.464333ms + duration: 630.015208ms - id: 2 request: proto: HTTP/1.1 @@ -114,15 +112,15 @@ interactions: - application/json status: 200 OK code: 200 - duration: 1.283017s + duration: 1.104417125s - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 51963 + content_length: 51878 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_c1c1d9c4d3814512a37b5ad4\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go func main\\\",\\\"count\\\":10}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| func main() {\\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func greeting() {\\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n## Result 2: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/02_func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/02_func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func main() {\\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\tgreeting := func() {\\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n```\\n\\n## Result 3: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n\",\"tool_call_id\":\"call_c1c1d9c4d3814512a37b5ad4\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/sourcegraph_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use sourcegraph to search for 'func main' in Go repositories\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_2373c4cfefc140738398b8e6\",\"function\":{\"arguments\":\"{\\\"query\\\":\\\"lang:go func main\\\"}\",\"name\":\"sourcegraph\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"# Sourcegraph Search Results\\n\\nFound 30 matches across 30 results\\n(Result limit reached, try a more specific query)\\n\\n## Result 1: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/01_before-func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| func main() {\\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func greeting() {\\n5| func greeting() {\\n6| \\tfmt.Println(\\\"Hello world!\\\")\\n7| }\\n8| \\n9| func main() {\\n10| \\tgreeting()\\n11| }\\n12| \\n```\\n\\n## Result 2: github.com/GoesToEleven/GolangTraining/14_functions/10_func-expression/02_func-expression/main.go\\n\\nURL: /github.com/GoesToEleven/GolangTraining/-/blob/14_functions/10_func-expression/02_func-expression/main.go\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func main() {\\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\tgreeting := func() {\\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n11| \\tgreeting()\\n12| }\\n13| \\n```\\n\\n```\\n0| package main\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func main() {\\n6| \\n7| \\tgreeting := func() {\\n8| \\t\\tfmt.Println(\\\"Hello world!\\\")\\n9| \\t}\\n10| \\n```\\n\\n## Result 3: github.com/jcalabro/uscope/assets/gobacktrace/main.go\\n\\nURL: /github.com/jcalabro/uscope/-/blob/assets/gobacktrace/main.go\\n\\n```\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| func main() {\\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| \\tFuncA()\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncB()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncC()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncD()\\n38| \\tFuncD()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncE()\\n39| \\tFuncE()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n34| func main() {\\n35| \\tFuncA()\\n36| \\tFuncB()\\n37| \\tFuncC()\\n38| \\tFuncD()\\n39| \\tFuncF()\\n40| \\tFuncF()\\n41| }\\n42| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| func FuncE() {\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| \\tfmt.Println(\\\"FuncE\\\")\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| func FuncD() {\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| \\tFuncE()\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n```\\n\\n```\\n1| package main\\n2| \\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tfmt.Println(\\\"FuncD\\\")\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n```\\n\\n```\\n3| import \\\"fmt\\\"\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| func FuncC() {\\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n```\\n\\n```\\n4| \\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| \\tFuncD()\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n```\\n\\n```\\n5| func FuncE() {\\n6| \\tfmt.Println(\\\"FuncE\\\")\\n7| }\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tfmt.Println(\\\"FuncC\\\")\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n```\\n\\n```\\n8| \\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| func FuncB() {\\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n```\\n\\n```\\n9| func FuncD() {\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| \\tFuncC()\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n```\\n\\n```\\n10| \\tFuncE()\\n11| \\tfmt.Println(\\\"FuncD\\\")\\n12| }\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tfmt.Println(\\\"FuncB\\\")\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| \\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n```\\n\\n```\\n13| \\n14| func FuncC() {\\n15| \\tFuncD()\\n16| \\tfmt.Println(\\\"FuncC\\\")\\n17| }\\n18| \\n19| func FuncB() {\\n20| \\tFuncC()\\n21| \\tfmt.Println(\\\"FuncB\\\")\\n22| }\\n23| func FuncA() {\\n24| func FuncA() {\\n25| \\tFuncB()\\n26| \\tfmt.Println(\\\"FuncA\\\")\\n27| }\\n28| \\n29| func FuncF() {\\n30| \\tfmt.Println(\\\"FuncF\\\")\\n31| \\tFuncE()\\n32| }\\n33| \\n```\\n\\n\",\"tool_call_id\":\"call_2373c4cfefc140738398b8e6\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -138,69 +136,75 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} + + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Found"}}]} + + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" "}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"30"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Found"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" matches"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" "}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" for"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"30"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" `"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" matches"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"func"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" across"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" Go"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"`"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" repositories"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" in"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" Results"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" repositories"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" show"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" various"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Results"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" `"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" include"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"func"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" training"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" examples"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"`"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" implementations"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" various"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" including"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Go"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" simple"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" programs"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" training"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" from"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" examples"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" repositories"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" and"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" like"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" more"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" G"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" complex"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"olang"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" applications"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Training"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" with"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" function"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" us"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" call"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"cope"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" chains"}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" projects"}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"202510272050452dc2c4868afb47af","created":1761569445,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":13380,"completion_tokens":34,"total_tokens":13414,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282259455a7f31f6052d4be7","created":1761663585,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":13356,"completion_tokens":37,"total_tokens":13393,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -209,4 +213,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.047079291s + duration: 919.849042ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/update_a_file.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/update_a_file.yaml index 1cdd8ca54dc250007df75d80914b29c3ffa6f83b..410780eb460b233c544a0686afeba8084334b773 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/update_a_file.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/update_a_file.yaml @@ -24,23 +24,25 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Update"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Update"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" to"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" to"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" print"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" print"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" hello"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" hello"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" message"}}]} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" from"}}]} - data: {"id":"202510272050027d15b1bf6019492e","created":1761569402,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":134,"completion_tokens":11,"total_tokens":145,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" crush"}}]} + + data: {"id":"2025102822582113fc68da71c44ae7","created":1761663501,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":134,"completion_tokens":12,"total_tokens":146,"prompt_tokens_details":{"cached_tokens":114}}} data: [DONE] @@ -49,15 +51,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 880.1925ms + duration: 916.907458ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44228 + content_length: 44156 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -73,139 +75,177 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" update"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"The"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" by"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" changing"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" wants"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" a"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" print"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" statement"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" update"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" say"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \""}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"hello"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" from"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" crush"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" change"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\"."}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" print"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" statement"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":":\n\n"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" say"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"1"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \""}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"hello"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" First"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" from"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" crush"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\"."}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" First"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" I"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"2"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" find"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" and"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Read"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" read"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" it"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" see"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" what"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" see"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" print"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" what"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" statement"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"'s"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" looks"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" currently"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" like"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" there"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":","}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"3"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" then"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" make"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Edit"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" it"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" specific"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" change"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" change"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" requested"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".\n\n"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" print"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Let"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" to"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" \""}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" start"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"hello"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" by"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" from"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" looking"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" crush"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" for"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\"\n"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"4"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" Test"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" in"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" change"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" if"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" current"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" possible"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" directory"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n\n"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Let"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" me"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_00fe173104784fcb96f897e3","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"main.go\"}"}}]}}]} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" start"}}]} - data: {"id":"202510272050028124c90f75554e54","created":1761569402,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10643,"completion_tokens":81,"total_tokens":10724,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" by"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" finding"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" the"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" main"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":".go"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" file"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_1dbca8706f7c4525b02a0169","index":0,"type":"function","function":{"name":"glob","arguments":"{\"pattern\":\"**/main.go\"}"}}]}}]} + + data: {"id":"202510282258217f7db04cef4c47dd","created":1761663501,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10627,"completion_tokens":102,"total_tokens":10729,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -214,15 +254,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.099010666s + duration: 15.323525958s - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44542 + content_length: 44473 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_00fe173104784fcb96f897e3\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_00fe173104784fcb96f897e3\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_1dbca8706f7c4525b02a0169\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_1dbca8706f7c4525b02a0169\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -238,13 +278,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050045d6f23bc99214907","created":1761569404,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225848202f414c561b4ba6","created":1761663528,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272050045d6f23bc99214907","created":1761569404,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225848202f414c561b4ba6","created":1761663528,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"202510272050045d6f23bc99214907","created":1761569404,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_45ba05dbca164eeba05c0d0c","index":0,"type":"function","function":{"name":"view","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\"}"}}]}}]} + data: {"id":"20251028225848202f414c561b4ba6","created":1761663528,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_17ae9185694a4283b7a3ae03","index":0,"type":"function","function":{"name":"view","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\"}"}}]}}]} - data: {"id":"202510272050045d6f23bc99214907","created":1761569404,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10686,"completion_tokens":36,"total_tokens":10722,"prompt_tokens_details":{"cached_tokens":45}}} + data: {"id":"20251028225848202f414c561b4ba6","created":1761663528,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10672,"completion_tokens":36,"total_tokens":10708,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -253,15 +293,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.509204458s + duration: 632.079875ms - id: 3 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45003 + content_length: 44934 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_00fe173104784fcb96f897e3\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_00fe173104784fcb96f897e3\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_45ba05dbca164eeba05c0d0c\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_45ba05dbca164eeba05c0d0c\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_1dbca8706f7c4525b02a0169\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_1dbca8706f7c4525b02a0169\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_17ae9185694a4283b7a3ae03\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_17ae9185694a4283b7a3ae03\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -277,13 +317,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205006fc03928038a44b8c","created":1761569406,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225849bbce80c093624e4b","created":1761663529,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205006fc03928038a44b8c","created":1761569406,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225849bbce80c093624e4b","created":1761663529,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205006fc03928038a44b8c","created":1761569406,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_7a055022b4a34b3093e3387e","index":0,"type":"function","function":{"name":"edit","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"old_string\":\"\\tfmt.Println(\\\"Hello, World!\\\")\",\"new_string\":\"\\tfmt.Println(\\\"hello from crush\\\")\"}"}}]}}]} + data: {"id":"20251028225849bbce80c093624e4b","created":1761663529,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_3d7f707f9a9d49a19e405fa9","index":0,"type":"function","function":{"name":"edit","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"old_string\":\"\\tfmt.Println(\\\"Hello, World!\\\")\",\"new_string\":\"\\tfmt.Println(\\\"Hello from crush\\\")\"}"}}]}}]} - data: {"id":"20251027205006fc03928038a44b8c","created":1761569406,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10779,"completion_tokens":66,"total_tokens":10845,"prompt_tokens_details":{"cached_tokens":10645}}} + data: {"id":"20251028225849bbce80c093624e4b","created":1761663529,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10765,"completion_tokens":66,"total_tokens":10831,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -292,15 +332,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 958.454084ms + duration: 656.745208ms - id: 4 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45541 + content_length: 45472 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_00fe173104784fcb96f897e3\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_00fe173104784fcb96f897e3\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_45ba05dbca164eeba05c0d0c\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_45ba05dbca164eeba05c0d0c\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_7a055022b4a34b3093e3387e\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_7a055022b4a34b3093e3387e\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_1dbca8706f7c4525b02a0169\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_1dbca8706f7c4525b02a0169\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_17ae9185694a4283b7a3ae03\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_17ae9185694a4283b7a3ae03\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_3d7f707f9a9d49a19e405fa9\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_3d7f707f9a9d49a19e405fa9\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -316,13 +356,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720500744340df3581c4343","created":1761569407,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225850f47bbd31ebbc4fe0","created":1761663530,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720500744340df3581c4343","created":1761569407,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225850f47bbd31ebbc4fe0","created":1761663530,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720500744340df3581c4343","created":1761569407,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_a65e9fa44e4b452f9ca9dd88","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"go run main.go\",\"description\":\"Test the updated program\"}"}}]}}]} + data: {"id":"20251028225850f47bbd31ebbc4fe0","created":1761663530,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_b006b8e35fee46fea7bd6af3","index":0,"type":"function","function":{"name":"bash","arguments":"{\"command\":\"cd /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file && go run main.go\",\"description\":\"Run the updated Go program to verify the change\"}"}}]}}]} - data: {"id":"2025102720500744340df3581c4343","created":1761569407,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10882,"completion_tokens":31,"total_tokens":10913,"prompt_tokens_details":{"cached_tokens":10844}}} + data: {"id":"20251028225850f47bbd31ebbc4fe0","created":1761663530,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10868,"completion_tokens":56,"total_tokens":10924,"prompt_tokens_details":{"cached_tokens":43}}} data: [DONE] @@ -331,15 +371,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 952.779167ms + duration: 1.152461209s - id: 5 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 45932 + content_length: 45948 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_00fe173104784fcb96f897e3\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_00fe173104784fcb96f897e3\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_45ba05dbca164eeba05c0d0c\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_45ba05dbca164eeba05c0d0c\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_7a055022b4a34b3093e3387e\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_7a055022b4a34b3093e3387e\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_a65e9fa44e4b452f9ca9dd88\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run main.go\\\",\\\"description\\\":\\\"Test the updated program\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"hello from crush\\n\\n\\n/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\",\"tool_call_id\":\"call_a65e9fa44e4b452f9ca9dd88\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_1dbca8706f7c4525b02a0169\",\"function\":{\"arguments\":\"{\\\"pattern\\\":\\\"**/main.go\\\"}\",\"name\":\"glob\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\",\"tool_call_id\":\"call_1dbca8706f7c4525b02a0169\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_17ae9185694a4283b7a3ae03\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n 1|package main\\n 2|\\n 3|import \\\"fmt\\\"\\n 4|\\n 5|func main() {\\n 6|\\tfmt.Println(\\\"Hello, World!\\\")\\n 7|}\\n\\n\",\"tool_call_id\":\"call_17ae9185694a4283b7a3ae03\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_3d7f707f9a9d49a19e405fa9\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\\",\\\"old_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\",\\\"new_string\\\":\\\"\\\\tfmt.Println(\\\\\\\"Hello from crush\\\\\\\")\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file/main.go\\n\\n\",\"tool_call_id\":\"call_3d7f707f9a9d49a19e405fa9\",\"role\":\"tool\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_b006b8e35fee46fea7bd6af3\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"cd /tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file && go run main.go\\\",\\\"description\\\":\\\"Run the updated Go program to verify the change\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"Hello from crush\\n\\n\\n/tmp/crush-test/TestCoderAgent/zai-glm4.6/update_a_file\",\"tool_call_id\":\"call_b006b8e35fee46fea7bd6af3\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -355,51 +395,47 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} - - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} - - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Done"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" The"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Done"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" main"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".go"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" Updated"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" file"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" main"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" now"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":".go"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" prints"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" to"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" \""}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" print"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"hello"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" \""}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" from"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" crush"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" from"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\""}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" crush"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" instead"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\""}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" of"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" and"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" \""}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" verified"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Hello"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" it"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":","}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" runs"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" World"}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" correctly"}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"!\"."}}]} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"202510272050096aa92bddfdc646d5","created":1761569409,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10945,"completion_tokens":25,"total_tokens":10970,"prompt_tokens_details":{"cached_tokens":45}}} + data: {"id":"20251028225853494586729df84ec7","created":1761663533,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10956,"completion_tokens":23,"total_tokens":10979,"prompt_tokens_details":{"cached_tokens":10707}}} data: [DONE] @@ -408,4 +444,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.471760334s + duration: 649.239333ms diff --git a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/write_tool.yaml b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/write_tool.yaml index 95fa929bfcc3aff7fef12aec28a480a8073b6c5c..4f557097096a8929bf4c6a5c47c696ae8a5291f9 100644 --- a/internal/agent/testdata/TestCoderAgent/zai-glm4.6/write_tool.yaml +++ b/internal/agent/testdata/TestCoderAgent/zai-glm4.6/write_tool.yaml @@ -24,21 +24,21 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Create"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":"Create"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" config"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" config"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".json"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":".json"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" file"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" test"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" with"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" version"}}]} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"delta":{"role":"assistant","content":" content"}}]} - data: {"id":"20251027205048e41cb9d9ad4d40ad","created":1761569448,"model":"glm-4.5-air","choices":[{"index":1,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":148,"completion_tokens":10,"total_tokens":158,"prompt_tokens_details":{"cached_tokens":4}}} + data: {"id":"2025102822594786437de495b64634","created":1761663587,"model":"glm-4.5-air","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":148,"completion_tokens":10,"total_tokens":158,"prompt_tokens_details":{"cached_tokens":115}}} data: [DONE] @@ -47,15 +47,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 600.723792ms + duration: 707.152875ms - id: 1 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44265 + content_length: 44193 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -71,13 +71,13 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"20251027205048543bed49e6a3408c","created":1761569448,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"202510282259471da9671da55a419f","created":1761663587,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"20251027205048543bed49e6a3408c","created":1761569448,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"202510282259471da9671da55a419f","created":1761663587,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"20251027205048543bed49e6a3408c","created":1761569448,"model":"glm-4.6","choices":[{"index":2,"delta":{"tool_calls":[{"id":"call_8afbb4da1af345afb3566838","index":0,"type":"function","function":{"name":"write","arguments":"{\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\",\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool/config.json\"}"}}]}}]} + data: {"id":"202510282259471da9671da55a419f","created":1761663587,"model":"glm-4.6","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_dd1fbff62a494f31939d0025","index":0,"type":"function","function":{"name":"write","arguments":"{\"file_path\":\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool/config.json\",\"content\":\"{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}\"}"}}]}}]} - data: {"id":"20251027205048543bed49e6a3408c","created":1761569448,"model":"glm-4.6","choices":[{"index":3,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10657,"completion_tokens":58,"total_tokens":10715,"prompt_tokens_details":{"cached_tokens":10595}}} + data: {"id":"202510282259471da9671da55a419f","created":1761663587,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"tool_calls","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10641,"completion_tokens":58,"total_tokens":10699,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -86,15 +86,15 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.401119875s + duration: 705.895542ms - id: 2 request: proto: HTTP/1.1 proto_major: 1 proto_minor: 1 - content_length: 44765 + content_length: 44693 host: "" - body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_8afbb4da1af345afb3566838\",\"function\":{\"arguments\":\"{\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\",\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool/config.json\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nFile successfully written: /tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool/config.json\\n\",\"tool_call_id\":\"call_8afbb4da1af345afb3566838\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\n\\n\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" + body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed). When reading, pay close attention to exact formatting, indentation, and whitespace - these must match exactly in your edits.\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act. Complete the ENTIRE task before stopping. Never stop mid-task. Never refuse work based on scope or complexity - break it down and do it.\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace, indentation, and line breaks\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n13. **COMPLETE THE TASK**: Never stop mid-task with \\\"Next:\\\" or \\\"Will do:\\\" statements. If you describe what needs to be done, DO IT immediately. Only stop when everything is finished.\\n14. **NEVER REFUSE BASED ON SCOPE**: Never refuse tasks because they seem large or complex. Break them into steps and complete them. Only stop if you encounter actual blocking errors (missing dependencies, compile failures, etc.), not perceived difficulty.\\n\\n\\n\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n\\n\\n\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n\\n\\n\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Before editing: verify exact whitespace and indentation from View output\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- If edit fails: read more context, don't guess - the text must match exactly\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) BUT IMMEDIATELY CONTINUE WORKING - progress updates are not stopping points\\n\\n**Before finishing**:\\n- Verify ENTIRE query is resolved (not just first step)\\n- All described next steps must be completed\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n\\n\\n\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only stop/ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts and hit actual blocking errors\\n\\n**Never stop for**:\\n- Task seems too large (break it down)\\n- Multiple files to change (change them)\\n- Concerns about \\\"session limits\\\" (no such limits exist)\\n- Work will take many steps (do all the steps)\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n\\n\\n\\n**No task is too large**:\\n- Break complex tasks into logical steps\\n- Complete each step fully before moving to next\\n- If a task has 10 parts, do all 10 parts\\n- Don't estimate effort or refuse based on scope\\n- Only stop if you hit actual errors (compile failures, missing files, etc.)\\n\\n**For large refactors or implementations**:\\n- Start with core functionality\\n- Build incrementally\\n- Test at each step\\n- Keep going until fully complete\\n\\nThere are no \\\"session limits\\\" - continue until the task is done or you hit a real blocker.\\n\\n\\n\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first - note the EXACT indentation (spaces vs tabs, count)\\n2. Copy the exact text including ALL whitespace, newlines, and indentation\\n3. Include 3-5 lines of context before and after the target\\n4. Verify your old_string would appear exactly once in the file\\n5. If uncertain about whitespace, include more surrounding context\\n6. Verify edit succeeded\\n7. Run tests\\n\\n**Whitespace matters**:\\n- Count spaces/tabs carefully (use View tool line numbers as reference)\\n- Include blank lines if they exist\\n- Match line endings exactly\\n- When in doubt, include MORE context rather than less\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation (spaces vs tabs, wrong count)\\n- Missing or extra blank lines\\n- Not enough context (text appears multiple times)\\n- Trimming whitespace that exists in the original\\n- Not testing after changes\\n\\n\\n\\nThe Edit tool is extremely literal. \\\"Close enough\\\" will fail.\\n\\n**Before every edit**:\\n1. View the file and locate the exact lines to change\\n2. Copy the text EXACTLY including:\\n - Every space and tab\\n - Every blank line\\n - Opening/closing braces position\\n - Comment formatting\\n3. Include enough surrounding lines (3-5) to make it unique\\n4. Double-check indentation level matches\\n\\n**Common failures**:\\n- `func foo() {` vs `func foo(){` (space before brace)\\n- Tab vs 4 spaces vs 2 spaces\\n- Missing blank line before/after\\n- `// comment` vs `//comment` (space after //)\\n- Different number of spaces in indentation\\n\\n**If edit fails**:\\n- View the file again at the specific location\\n- Copy even more context\\n- Check for tabs vs spaces\\n- Verify line endings\\n- Try including the entire function/block if needed\\n- Never retry with guessed changes - get the exact text first\\n\\n\\n\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n\\n**Edit tool \\\"old_string not found\\\"**:\\n- View the file again at the target location\\n- Copy the EXACT text including all whitespace\\n- Include more surrounding context (full function if needed)\\n- Check for tabs vs spaces, extra/missing blank lines\\n- Count indentation spaces carefully\\n- Don't retry with approximate matches - get the exact text\\n\\n\\n\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences \\n- Important codebase patterns\\n- Useful project information\\n\\n\\n\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n\\n\\n\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n\\n\\n\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n\\n\\n\\n\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including ALL follow-ups and \\\"next steps\\\")\\n- Never describe what you'll do next - just do it\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n\\n\\n\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n\\n\\n\\nWorking directory: /tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"use write to create a new file called config.json with content '{\\\"name\\\": \\\"test\\\", \\\"version\\\": \\\"1.0.0\\\"}'\",\"role\":\"user\"},{\"content\":\"\\n\",\"tool_calls\":[{\"id\":\"call_dd1fbff62a494f31939d0025\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool/config.json\\\",\\\"content\\\":\\\"{\\\\\\\"name\\\\\\\": \\\\\\\"test\\\\\\\", \\\\\\\"version\\\\\\\": \\\\\\\"1.0.0\\\\\\\"}\\\"}\",\"name\":\"write\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\nFile successfully written: /tmp/crush-test/TestCoderAgent/zai-glm4.6/write_tool/config.json\\n\",\"tool_call_id\":\"call_dd1fbff62a494f31939d0025\",\"role\":\"tool\"}],\"model\":\"glm-4.6\",\"max_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"web_fetch\",\"strict\":false,\"description\":\"Fetches content from a web URL (for use by sub-agents).\\n\\n\\n- Provide a URL to fetch\\n- The tool fetches the content and returns it as markdown\\n- Use this when you need to follow links from the current page\\n- After fetching, analyze the content to answer the user's question\\n\\n\\n\\n- Automatically converts HTML to markdown for easier analysis\\n- For large pages (>50KB), saves content to a temporary file and provides the path\\n- You can then use grep/view tools to search through the file\\n- Handles UTF-8 content validation\\n\\n\\n\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n\\n\\n\\n- For large pages saved to files, use grep to find relevant sections first\\n- Don't fetch unnecessary pages - only when needed to answer the question\\n- Focus on extracting specific information from the fetched content\\n\\n\",\"parameters\":{\"properties\":{\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n\\n\\n\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with tags\\n\\n\\n\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n\\n\\n\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in tags:\\n - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n - Don't use tools beyond git context\\n - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n git commit -m \\\"$(cat <<'EOF'\\n Commit message here.\\n\\n \U0001F498 Generated with Crush\\n\\n\\n Co-Authored-By: Crush \\n\\n EOF\\n )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\n\\n\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n - git status (untracked files)\\n - git diff (staged/unstaged changes)\\n - Check if branch tracks remote and is up to date\\n - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in tags:\\n - List commits since diverging from main\\n - Summarize nature of changes\\n - Brainstorm purpose/motivation\\n - Assess project impact\\n - Don't use tools beyond git context\\n - Check for sensitive information\\n - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n - Ensure summary reflects ALL changes since main divergence\\n - Clear, concise language\\n - Accurate reflection of changes and purpose\\n - Avoid generic summaries\\n - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n gh pr create --title \\\"title\\\" --body \\\"$(cat <<'EOF'\\n\\n ## Summary\\n\\n <1-3 bullet points>\\n\\n ## Test plan\\n\\n [Checklist of TODOs...]\\n\\n\\n \U0001F498 Generated with Crush\\n\\n\\n EOF\\n )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n\\n\\n\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\n\\n\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n\\n\\n\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n\\n\\n\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n3. **CRITICAL**: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n\\n\\n\\n\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n \\n\\n\\nEXACT MATCHING: The tool is extremely literal. Text must match **EXACTLY**\\n\\n- Every space and tab character\\n- Every blank line\\n- Every newline character\\n- Indentation level (count the spaces/tabs)\\n- Comment spacing (`// comment` vs `//comment`)\\n- Brace positioning (`func() {` vs `func(){`)\\n\\nCommon failures:\\n\\n```\\nExpected: \\\" func foo() {\\\" (4 spaces)\\nProvided: \\\" func foo() {\\\" (2 spaces) ❌ FAILS\\n\\nExpected: \\\"}\\\\n\\\\nfunc bar() {\\\" (2 newlines)\\nProvided: \\\"}\\\\nfunc bar() {\\\" (1 newline) ❌ FAILS\\n\\nExpected: \\\"// Comment\\\" (space after //)\\nProvided: \\\"//Comment\\\" (no space) ❌ FAILS\\n```\\n\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n- If text appears multiple times, add more context to make it unique\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION BEFORE USING: Before every edit\\n\\n1. View the file and locate exact target location\\n2. Check how many instances of target text exist\\n3. Copy the EXACT text including all whitespace\\n4. Verify you have enough context for unique identification\\n5. Double-check indentation matches (count spaces/tabs)\\n6. Plan separate calls or use replace_all for multiple changes\\n \\n\\n\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n- Indentation is off by even one space\\n- Missing or extra blank lines\\n- Wrong tabs vs spaces\\n\\n\\n\\nIf you get \\\"old_string not found in file\\\":\\n\\n1. **View the file again** at the specific location\\n2. **Copy more context** - include entire function if needed\\n3. **Check whitespace**:\\n - Count indentation spaces/tabs\\n - Look for blank lines\\n - Check for trailing spaces\\n4. **Verify character-by-character** that your old_string matches\\n5. **Never guess** - always View the file to get exact text\\n \\n\\n\\n\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n- **When in doubt, include MORE context rather than less**\\n- Match the existing code style exactly (spaces, tabs, blank lines)\\n \\n\\n\\nBefore submitting an edit, verify:\\n\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if they exist\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3-5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all)\\n- [ ] Copied text character-for-character, not approximated\\n \\n\\n\\n✅ Correct: Exact match with context\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n\\nnew_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n // New validation\\\\n if len(input) > 1000 {\\\\n return errors.New(\\\\\\\"input too long\\\\\\\")\\\\n }\\\\n return nil\\\\n}\\\"\\n```\\n\\n❌ Incorrect: Not enough context\\n\\n```\\nold_string: \\\"return nil\\\" // Appears many times!\\n```\\n\\n❌ Incorrect: Wrong indentation\\n\\n```\\nold_string: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 2 spaces\\n// But file actually has: \\\" if input == \\\\\\\"\\\\\\\" {\\\" // 4 spaces\\n```\\n\\n✅ Correct: Including context to make unique\\n\\n```\\nold_string: \\\"func ProcessData(input string) error {\\\\n if input == \\\\\\\"\\\\\\\" {\\\\n return errors.New(\\\\\\\"empty input\\\\\\\")\\\\n }\\\\n return nil\\\"\\n```\\n\\n\\n\\n\\n\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n \\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n3. CRITICAL: Note exact whitespace, indentation, and formatting from View output\\n\\n\\n\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n - old_string: Text to replace (must match exactly including whitespace/indentation)\\n - new_string: Replacement text\\n - replace_all: Replace all occurrences (optional, defaults to false)\\n\\n\\n\\n- Edits applied sequentially in provided order.\\n- Each edit operates on result of previous edit.\\n- ATOMIC: If any single edit fails, the entire operation fails and no changes are applied.\\n- Ideal for several changes to different parts of same file.\\n\\n\\n\\nAll instructions from the Edit tool documentation apply verbatim to every edit item:\\n- Critical requirements for exact matching and uniqueness\\n- Warnings and common failures (tabs vs spaces, blank lines, brace placement, etc.)\\n- Verification steps before using, recovery steps, best practices, and whitespace checklist\\nUse the same level of precision as Edit. Multiedit often fails due to formatting mismatches—double-check whitespace for every edit.\\n\\n\\n\\n1. Apply Edit tool rules to EACH edit (see edit.md).\\n2. Edits are atomic—either all succeed or none are applied.\\n3. Plan sequence carefully: earlier edits change the file content that later edits must match.\\n4. Ensure each old_string is unique at its application time (after prior edits).\\n\\n\\n\\n1. View the file and copy exact text (including whitespace) for each target.\\n2. Check how many instances each old_string has BEFORE the sequence starts.\\n3. Dry-run mentally: after applying edit #N, will edit #N+1 still match? Adjust old_string/new_string accordingly.\\n4. Prefer fewer, larger context blocks over many tiny fragments that are easy to misalign.\\n5. If edits are independent, consider separate multiedit batches per logical region.\\n\\n\\n\\n- Operation fails if any old_string doesn’t match exactly (including whitespace) or equals new_string.\\n- Earlier edits can invalidate later matches (added/removed spaces, lines, or reordered text).\\n- Mixed tabs/spaces, trailing spaces, or missing blank lines commonly cause failures.\\n- replace_all may affect unintended regions—use carefully or provide more context.\\n\\n\\n\\nIf the operation fails:\\n1. Identify the first failing edit (start from top; test subsets to isolate).\\n2. View the file again and copy more surrounding context for that edit.\\n3. Recalculate later old_string values based on the file state AFTER preceding edits.\\n4. Reduce the batch (apply earlier stable edits first), then follow up with the rest.\\n\\n\\n\\n- Ensure all edits result in correct, idiomatic code; don’t leave code broken.\\n- Use absolute file paths (starting with /).\\n- Use replace_all only when you’re certain; otherwise provide unique context.\\n- Match existing style exactly (spaces, tabs, blank lines).\\n- Test after the operation; if it fails, fix and retry in smaller chunks.\\n\\n\\n\\nFor EACH edit, verify:\\n- [ ] Viewed the file first\\n- [ ] Counted indentation spaces/tabs\\n- [ ] Included blank lines if present\\n- [ ] Matched brace/bracket positioning\\n- [ ] Included 3–5 lines of surrounding context\\n- [ ] Verified text appears exactly once (or using replace_all deliberately)\\n- [ ] Copied text character-for-character, not approximated\\n\\n\\n\\n✅ Correct: Sequential edits where the second match accounts for the first change\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n doNew()\\\\n}\\\",\\n },\\n {\\n // Uses context that still exists AFTER the first replacement\\n old_string: \\\"func B() {\\\\n callA()\\\\n}\\\",\\n new_string: \\\"func B() {\\\\n callA()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n❌ Incorrect: Second old_string no longer matches due to whitespace change introduced by the first edit\\n\\n```\\nedits: [\\n {\\n old_string: \\\"func A() {\\\\n doOld()\\\\n}\\\",\\n new_string: \\\"func A() {\\\\n\\\\n doNew()\\\\n}\\\", // Added extra blank line\\n },\\n {\\n old_string: \\\"func A() {\\\\n doNew()\\\\n}\\\", // Missing the new blank line, will FAIL\\n new_string: \\\"func A() {\\\\n doNew()\\\\n logChange()\\\\n}\\\",\\n },\\n]\\n```\\n\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n\\n\\n\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n\\n\\n\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n\\n\\n\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n\\n\\n\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n\\n\\n\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\n\\n\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n\\n\\n\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n\\n\\n\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n\\n\\n\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\n\\n\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n\\n\\n\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n\\n\\n\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n\\n\\n\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\n\\n\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n\\n\\n\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n\\n\\n\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n\\n\\n\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n\\n\\n\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\n\\n\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n\\n\\n\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n\\n\\n\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\n\\n\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n\\n\\n\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\n\\n\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n\\n\\n\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\n\\n\\n- Use forward slashes (/) for compatibility\\n\\n\\n\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}" headers: Accept: - application/json @@ -110,25 +110,19 @@ interactions: proto_minor: 0 content_length: -1 body: |+ - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"\n"}}]} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"","reasoning_content":"\n"}}]} - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"\n"}}]} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"\n"}}]} - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"Created"}}]} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"File"}}]} - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" config"}}]} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" created"}}]} - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":".json"}}]} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":" successfully"}}]} - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" with"}}]} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"."}}]} - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" test"}}]} - - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":" configuration"}}]} - - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":1,"delta":{"role":"assistant","content":"."}}]} - - data: {"id":"2025102720505052f9c265268842dc","created":1761569450,"model":"glm-4.6","choices":[{"index":2,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10750,"completion_tokens":12,"total_tokens":10762,"prompt_tokens_details":{"cached_tokens":10714}}} + data: {"id":"20251028225949e856bf8ac131426b","created":1761663589,"model":"glm-4.6","choices":[{"index":0,"finish_reason":"stop","delta":{"role":"assistant","content":""}}],"usage":{"prompt_tokens":10734,"completion_tokens":9,"total_tokens":10743,"prompt_tokens_details":{"cached_tokens":10579}}} data: [DONE] @@ -137,4 +131,4 @@ interactions: - text/event-stream;charset=UTF-8 status: 200 OK code: 200 - duration: 1.793792708s + duration: 611.143584ms